Merge 5487ef17bc into 4e88f48a71

Signed-off-by: Leo Siepel <leosiepel@gmail.com>

bundles/org.openhab.binding.digiplex/src/main/java/org/openhab/binding/digiplex/internal/communication/ErroneousResponse.java

@@ -1,4 +1,4 @@
-/**
+/*
  * Copyright (c) 2010-2025 Contributors to the openHAB project
  *
  * See the NOTICE file(s) distributed with this work for additional

bundles/org.openhab.binding.digiplex/src/test/java/org/openhab/binding/digiplex/internal/communication/DigiplexResponseResolverTest.java

@@ -1,4 +1,4 @@
-/**
+/*
  * Copyright (c) 2010-2025 Contributors to the openHAB project
  *
  * See the NOTICE file(s) distributed with this work for additional

bundles/org.openhab.binding.roku/README.md

@@ -46,6 +46,8 @@ The following channels are available:
 | playMode           | String               | The current playback mode ie: stop, play, pause (ReadOnly).                                                                                                     |
 | timeElapsed        | Number:Time          | The total number of seconds of playback time elapsed for the current playing title (ReadOnly).                                                                  |
 | timeTotal          | Number:Time          | The total length of the current playing title in seconds (ReadOnly). This data is not provided by all streaming apps.                                           |
+| endTime            | DateTime             | The date/time when the currently playing media will end (ReadOnly). N/A if timeTotal is not provided by the current streaming app.                              |
+| progress           | Dimmer               | The current progress [0-100%] of playing media (ReadOnly). N/A if timeTotal is not provided by the current streaming app.                                       |
 | activeChannel      | String               | A dropdown containing a list of available TV channels on the Roku TV. The channel currently tuned is automatically selected. The list updates every 10 minutes. |
 | signalMode         | String               | The signal type of the current TV channel, ie: 1080i (ReadOnly).                                                                                                |
 | signalQuality      | Number:Dimensionless | The signal quality of the current TV channel, 0-100% (ReadOnly).                                                                                                |
@@ -59,6 +61,7 @@ The following channels are available:
 Some Notes:
 
 - The values for `activeApp`, `activeAppName`, `playMode`, `timeElapsed`, `timeTotal`, `activeChannel`, `signalMode`, `signalQuality`, `channelName`, `programTitle`, `programDescription`, `programRating`, `power` & `powerState` refresh automatically per the configured `refresh` interval.
+- The `endTime` and `progress` channels may not be accurate for some streaming apps especially 'live' streams where the `timeTotal` value constantly increases.
 
 **List of available button commands for Roku streaming devices:**
 
@@ -113,32 +116,36 @@ roku:roku_tv:mytv1 "My Roku TV" [ hostName="192.168.10.1", refresh=10 ]
 ```java
 // Roku streaming media player items:
 
-String Player_ActiveApp        "Current App: [%s]"         { channel="roku:roku_player:myplayer1:activeApp" }
+String Player_ActiveApp        "Current App: [%s]"             { channel="roku:roku_player:myplayer1:activeApp" }
-String Player_ActiveAppName    "Current App Name: [%s]"    { channel="roku:roku_player:myplayer1:activeAppName" }
+String Player_ActiveAppName    "Current App Name: [%s]"        { channel="roku:roku_player:myplayer1:activeAppName" }
-String Player_Button           "Send Command to Roku"      { channel="roku:roku_player:myplayer1:button" }
+String Player_Button           "Send Command to Roku"          { channel="roku:roku_player:myplayer1:button" }
-Player Player_Control          "Control"                   { channel="roku:roku_player:myplayer1:control" }
+Player Player_Control          "Control"                       { channel="roku:roku_player:myplayer1:control" }
-String Player_PlayMode         "Status: [%s]"              { channel="roku:roku_player:myplayer1:playMode" }
+String Player_PlayMode         "Status: [%s]"                  { channel="roku:roku_player:myplayer1:playMode" }
-Number:Time Player_TimeElapsed "Elapsed Time: [%d %unit%]" { channel="roku:roku_player:myplayer1:timeElapsed" }
+Number:Time Player_TimeElapsed "Elapsed Time: [%d %unit%]"     { channel="roku:roku_player:myplayer1:timeElapsed" }
-Number:Time Player_TimeTotal   "Total Time: [%d %unit%]"   { channel="roku:roku_player:myplayer1:timeTotal" }
+Number:Time Player_TimeTotal   "Total Time: [%d %unit%]"       { channel="roku:roku_player:myplayer1:timeTotal" }
+DateTime Player_EndTime        "End Time: [%1$tl:%1$tM %1$tp]" { channel="roku:roku_player:myplayer1:endTime" }
+Dimmer Player_Progress         "Progress [%.0f%%]"             { channel="roku:roku_player:myplayer1:progress" }
 
 // Roku TV items:
 
-Switch Player_Power              "Power: [%s]"               { channel="roku:roku_tv:mytv1:power" }
+Switch Player_Power              "Power: [%s]"                   { channel="roku:roku_tv:mytv1:power" }
-String Player_PowerState         "Power State: [%s]          { channel="roku:roku_tv:mytv1:powerState" }
+String Player_PowerState         "Power State: [%s]              { channel="roku:roku_tv:mytv1:powerState" }
-String Player_ActiveApp          "Current App: [%s]"         { channel="roku:roku_tv:mytv1:activeApp" }
+String Player_ActiveApp          "Current App: [%s]"             { channel="roku:roku_tv:mytv1:activeApp" }
-String Player_ActiveAppName      "Current App Name: [%s]"    { channel="roku:roku_tv:mytv1:activeAppName" }
+String Player_ActiveAppName      "Current App Name: [%s]"        { channel="roku:roku_tv:mytv1:activeAppName" }
-String Player_Button             "Send Command to Roku"      { channel="roku:roku_tv:mytv1:button" }
+String Player_Button             "Send Command to Roku"          { channel="roku:roku_tv:mytv1:button" }
-Player Player_Control            "Control"                   { channel="roku:roku_tv:mytv1:control" }
+Player Player_Control            "Control"                       { channel="roku:roku_tv:mytv1:control" }
-String Player_PlayMode           "Status: [%s]"              { channel="roku:roku_tv:mytv1:playMode" }
+String Player_PlayMode           "Status: [%s]"                  { channel="roku:roku_tv:mytv1:playMode" }
-Number:Time Player_TimeElapsed   "Elapsed Time: [%d %unit%]" { channel="roku:roku_tv:mytv1:timeElapsed" }
+Number:Time Player_TimeElapsed   "Elapsed Time: [%d %unit%]"     { channel="roku:roku_tv:mytv1:timeElapsed" }
-Number:Time Player_TimeTotal     "Total Time: [%d %unit%]"   { channel="roku:roku_tv:mytv1:timeTotal" }
+Number:Time Player_TimeTotal     "Total Time: [%d %unit%]"       { channel="roku:roku_tv:mytv1:timeTotal" }
-String Player_ActiveChannel      "Current Channel: [%s]"     { channel="roku:roku_tv:mytv1:activeChannel" }
+DateTime Player_EndTime          "End Time: [%1$tl:%1$tM %1$tp]" { channel="roku:roku_tv:mytv1:endTime" }
-String Player_SignalMode         "Signal Mode: [%s]"         { channel="roku:roku_tv:mytv1:signalMode" }
+Dimmer Player_Progress           "Progress [%.0f%%]"             { channel="roku:roku_tv:mytv1:progress" }
-Number Player_SignalQuality      "Signal Quality: [%d %%]"   { channel="roku:roku_tv:mytv1:signalQuality" }
+String Player_ActiveChannel      "Current Channel: [%s]"         { channel="roku:roku_tv:mytv1:activeChannel" }
-String Player_ChannelName        "Channel Name: [%s]"        { channel="roku:roku_tv:mytv1:channelName" }
+String Player_SignalMode         "Signal Mode: [%s]"             { channel="roku:roku_tv:mytv1:signalMode" }
-String Player_ProgramTitle       "Program Title: [%s]"       { channel="roku:roku_tv:mytv1:programTitle" }
+Number Player_SignalQuality      "Signal Quality: [%d %%]"       { channel="roku:roku_tv:mytv1:signalQuality" }
-String Player_ProgramDescription "Program Description: [%s]" { channel="roku:roku_tv:mytv1:programDescription" }
+String Player_ChannelName        "Channel Name: [%s]"            { channel="roku:roku_tv:mytv1:channelName" }
-String Player_ProgramRating      "Program Rating: [%s]"      { channel="roku:roku_tv:mytv1:programRating" }
+String Player_ProgramTitle       "Program Title: [%s]"           { channel="roku:roku_tv:mytv1:programTitle" }
+String Player_ProgramDescription "Program Description: [%s]"     { channel="roku:roku_tv:mytv1:programDescription" }
+String Player_ProgramRating      "Program Rating: [%s]"          { channel="roku:roku_tv:mytv1:programRating" }
 ```
 
 ### `roku.sitemap` Example
@@ -154,6 +161,8 @@ sitemap roku label="Roku" {
         Text item=Player_PlayMode
         Text item=Player_TimeElapsed icon="time"
         Text item=Player_TimeTotal icon="time"
+        Text item=Player_EndTime icon="time"
+        Slider item=Player_Progress icon="time"
         // The following items apply to Roku TVs only
         Switch item=Player_Power
         Text item=Player_PowerState

bundles/org.openhab.binding.roku/src/main/java/org/openhab/binding/roku/internal/RokuBindingConstants.java

@@ -55,6 +55,8 @@ public class RokuBindingConstants {
     public static final String PLAY_MODE = "playMode";
     public static final String TIME_ELAPSED = "timeElapsed";
     public static final String TIME_TOTAL = "timeTotal";
+    public static final String END_TIME = "endTime";
+    public static final String PROGRESS = "progress";
     public static final String ACTIVE_CHANNEL = "activeChannel";
     public static final String SIGNAL_MODE = "signalMode";
     public static final String SIGNAL_QUALITY = "signalQuality";

bundles/org.openhab.binding.roku/src/main/java/org/openhab/binding/roku/internal/handler/RokuHandler.java

@@ -14,6 +14,8 @@ package org.openhab.binding.roku.internal.handler;
 
 import static org.openhab.binding.roku.internal.RokuBindingConstants.*;
 
+import java.math.BigDecimal;
+import java.time.Instant;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
@@ -34,8 +36,10 @@ import org.openhab.binding.roku.internal.dto.DeviceInfo;
 import org.openhab.binding.roku.internal.dto.Player;
 import org.openhab.binding.roku.internal.dto.TvChannel;
 import org.openhab.binding.roku.internal.dto.TvChannels.Channel;
+import org.openhab.core.library.types.DateTimeType;
 import org.openhab.core.library.types.NextPreviousType;
 import org.openhab.core.library.types.OnOffType;
+import org.openhab.core.library.types.PercentType;
 import org.openhab.core.library.types.PlayPauseType;
 import org.openhab.core.library.types.QuantityType;
 import org.openhab.core.library.types.StringType;
@@ -195,21 +199,32 @@ public class RokuHandler extends BaseThingHandler {
                             PLAY.equalsIgnoreCase(playerInfo.getState()) ? PlayPauseType.PLAY : PlayPauseType.PAUSE);
 
                     // Remove non-numeric from string, ie: ' ms'
-                    String position = playerInfo.getPosition().replaceAll(NON_DIGIT_PATTERN, EMPTY);
+                    final String positionStr = playerInfo.getPosition().replaceAll(NON_DIGIT_PATTERN, EMPTY);
-                    if (!EMPTY.equals(position)) {
+                    int position = -1;
-                        updateState(TIME_ELAPSED,
+                    if (!EMPTY.equals(positionStr)) {
-                                new QuantityType<>(Integer.parseInt(position) / 1000, API_SECONDS_UNIT));
+                        position = Integer.parseInt(positionStr) / 1000;
+                        updateState(TIME_ELAPSED, new QuantityType<>(position, API_SECONDS_UNIT));
                     } else {
                         updateState(TIME_ELAPSED, UnDefType.UNDEF);
                     }
 
-                    String duration = playerInfo.getDuration().replaceAll(NON_DIGIT_PATTERN, EMPTY);
+                    final String durationStr = playerInfo.getDuration().replaceAll(NON_DIGIT_PATTERN, EMPTY);
-                    if (!EMPTY.equals(duration)) {
+                    int duration = -1;
-                        updateState(TIME_TOTAL,
+                    if (!EMPTY.equals(durationStr)) {
-                                new QuantityType<>(Integer.parseInt(duration) / 1000, API_SECONDS_UNIT));
+                        duration = Integer.parseInt(durationStr) / 1000;
+                        updateState(TIME_TOTAL, new QuantityType<>(duration, API_SECONDS_UNIT));
                     } else {
                         updateState(TIME_TOTAL, UnDefType.UNDEF);
                     }
+
+                    if (position >= 0 && duration > 0) {
+                        updateState(END_TIME, new DateTimeType(Instant.now().plusSeconds(duration - position)));
+                        updateState(PROGRESS,
+                                new PercentType(BigDecimal.valueOf(Math.round(position / (double) duration * 100.0))));
+                    } else {
+                        updateState(END_TIME, UnDefType.UNDEF);
+                        updateState(PROGRESS, UnDefType.UNDEF);
+                    }
                 } catch (NumberFormatException e) {
                     logger.debug("Unable to parse playerInfo integer value. Exception: {}", e.getMessage());
                 } catch (RokuLimitedModeException e) {
@@ -224,6 +239,8 @@ public class RokuHandler extends BaseThingHandler {
                 updateState(PLAY_MODE, UnDefType.UNDEF);
                 updateState(TIME_ELAPSED, UnDefType.UNDEF);
                 updateState(TIME_TOTAL, UnDefType.UNDEF);
+                updateState(END_TIME, UnDefType.UNDEF);
+                updateState(PROGRESS, UnDefType.UNDEF);
             }
 
             if (thingTypeUID.equals(THING_TYPE_ROKU_TV) && tvActive) {

bundles/org.openhab.binding.roku/src/main/resources/OH-INF/i18n/roku.properties

@@ -80,6 +80,8 @@ channel-type.roku.channelName.label = Channel Name
 channel-type.roku.channelName.description = The Name of the Channel Currently Selected
 channel-type.roku.control.label = Control
 channel-type.roku.control.description = Control playback e.g. Play/Pause/Next/Previous
+channel-type.roku.endTime.label = End Time
+channel-type.roku.endTime.description = The date/time when the currently playing media will end
 channel-type.roku.playMode.label = Play Mode
 channel-type.roku.playMode.description = The Current Playback Mode
 channel-type.roku.powerState.label = Power State
@@ -93,6 +95,8 @@ channel-type.roku.programRating.label = Program Rating
 channel-type.roku.programRating.description = The TV Parental Guideline Rating of the Current TV Program
 channel-type.roku.programTitle.label = Program Title
 channel-type.roku.programTitle.description = The Name of the Current TV Program
+channel-type.roku.progress.label = Media Progress
+channel-type.roku.progress.description = The current progress of playing media
 channel-type.roku.signalMode.label = Signal Mode
 channel-type.roku.signalMode.description = The Signal Type of the Current TV Channel, ie: 1080i
 channel-type.roku.signalQuality.label = Signal Quality

bundles/org.openhab.binding.roku/src/main/resources/OH-INF/thing/roku.xml

@@ -19,6 +19,8 @@
 			<channel id="playMode" typeId="playMode"/>
 			<channel id="timeElapsed" typeId="timeElapsed"/>
 			<channel id="timeTotal" typeId="timeTotal"/>
+			<channel id="endTime" typeId="endTime"/>
+			<channel id="progress" typeId="progress"/>
 		</channels>
 
 		<properties>
@@ -28,7 +30,7 @@
 			<property name="Serial Number">unknown</property>
 			<property name="Device Id">unknown</property>
 			<property name="Software Version">unknown</property>
-			<property name="thingTypeVersion">1</property>
+			<property name="thingTypeVersion">2</property>
 		</properties>
 
 		<representation-property>uuid</representation-property>
@@ -52,6 +54,8 @@
 			<channel id="playMode" typeId="playMode"/>
 			<channel id="timeElapsed" typeId="timeElapsed"/>
 			<channel id="timeTotal" typeId="timeTotal"/>
+			<channel id="endTime" typeId="endTime"/>
+			<channel id="progress" typeId="progress"/>
 			<channel id="activeChannel" typeId="activeChannel"/>
 			<channel id="signalMode" typeId="signalMode"/>
 			<channel id="signalQuality" typeId="signalQuality"/>
@@ -69,7 +73,7 @@
 			<property name="Serial Number">unknown</property>
 			<property name="Device Id">unknown</property>
 			<property name="Software Version">unknown</property>
-			<property name="thingTypeVersion">1</property>
+			<property name="thingTypeVersion">2</property>
 		</properties>
 
 		<representation-property>uuid</representation-property>
@@ -185,6 +189,24 @@
 		<state readOnly="true" pattern="%d %unit%"/>
 	</channel-type>
 
+	<channel-type id="endTime">
+		<item-type>DateTime</item-type>
+		<label>End Time</label>
+		<description>The date/time when the currently playing media will end</description>
+		<category>Time</category>
+		<tags>
+			<tag>Status</tag>
+			<tag>Timestamp</tag>
+		</tags>
+		<state readOnly="true"/>
+	</channel-type>
+
+	<channel-type id="progress">
+		<item-type>Dimmer</item-type>
+		<label>Media Progress</label>
+		<description>The current progress of playing media</description>
+	</channel-type>
+
 	<channel-type id="activeChannel">
 		<item-type>String</item-type>
 		<label>Active Channel</label>

bundles/org.openhab.binding.roku/src/main/resources/OH-INF/update/update.xml

@@ -12,6 +12,15 @@
 				<type>roku:control</type>
 			</add-channel>
 		</instruction-set>
+
+		<instruction-set targetVersion="2">
+			<add-channel id="endTime">
+				<type>roku:endTime</type>
+			</add-channel>
+			<add-channel id="progress">
+				<type>roku:progress</type>
+			</add-channel>
+		</instruction-set>
 	</thing-type>
 
 	<thing-type uid="roku:roku_tv">
@@ -29,6 +38,15 @@
 				<type>roku:control</type>
 			</add-channel>
 		</instruction-set>
+
+		<instruction-set targetVersion="2">
+			<add-channel id="endTime">
+				<type>roku:endTime</type>
+			</add-channel>
+			<add-channel id="progress">
+				<type>roku:progress</type>
+			</add-channel>
+		</instruction-set>
 	</thing-type>
 
 </update:update-descriptions>

bundles/org.openhab.binding.tacmi/src/main/java/org/openhab/binding/tacmi/internal/schema/ApiPageParser.java

@@ -185,6 +185,7 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
                     } else if ("durchsichtig".equals(classFlag)) { // link
                         this.fieldType = FieldType.IGNORE;
                     } else if ("bord".equals(classFlag)) { // special button style - not of our interest...
+                        continue;
                     } else {
                         logger.debug("Unhanndled class in {}:{}:{}: '{}' ", id, line, col, classFlag);
                     }
@@ -192,7 +193,7 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
             }
         } else if (this.parserState == ParserState.DATA_ENTRY && this.fieldType == FieldType.BUTTON
                 && "span".equals(elementName)) {
-            // ignored...
+            return; // ignored...
         } else {
             logger.debug("Unexpected OpenElement in {}:{}: {} [{}]", line, col, elementName, attributes);
         }
@@ -245,14 +246,14 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
                         getApiPageEntry(id, line, col, shortName, description, this.buttonValue);
                     }
                 } else if (this.fieldType == FieldType.IGNORE) {
-                    // ignore
+                    return; // ignore
                 } else {
                     logger.debug("Unhandled setting {}:{}:{} [{}] : {}", id, line, col, this.fieldType, sb);
                 }
             }
         } else if (this.parserState == ParserState.DATA_ENTRY && this.fieldType == FieldType.BUTTON
                 && "span".equals(elementName)) {
-            // ignored...
+            return;// ignored...
         } else {
             logger.debug("Unexpected CloseElement in {}:{}: {}", line, col, elementName);
         }
@@ -307,7 +308,7 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
             }
         } else if (this.parserState == ParserState.INIT && ((len == 1 && buffer[offset] == '\n')
                 || (len == 2 && buffer[offset] == '\r' && buffer[offset + 1] == '\n'))) {
-            // single newline - ignore/drop it...
+            return; // single newline - ignore/drop it...
         } else {
             String msg = new String(buffer, offset, len).replace("\n", "\\n").replace("\r", "\\r");
             logger.debug("Unexpected Text {}:{}: ParserState: {} ({}) `{}`", line, col, parserState, len, msg);
@@ -400,9 +401,9 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
                                     // failed to get unit...
                                     if ("Imp".equals(unitStr) || "€$".contains(unitStr)) {
                                         // special case
-                                        unitData = taCmiSchemaHandler.SPECIAL_MARKER;
+                                        unitData = TACmiSchemaHandler.SPECIAL_MARKER;
                                     } else {
-                                        unitData = taCmiSchemaHandler.NULL_MARKER;
+                                        unitData = TACmiSchemaHandler.NULL_MARKER;
                                         logger.warn(
                                                 "Unhandled UoM '{}' - seen on channel {} '{}'; Message from QuantityType: {}",
                                                 valParts[1], shortName, description, iae.getMessage());
@@ -410,12 +411,12 @@ public class ApiPageParser extends AbstractSimpleMarkupHandler {
                                 }
                                 taCmiSchemaHandler.unitsCache.put(unitStr, unitData);
                             }
-                            if (unitData == taCmiSchemaHandler.NULL_MARKER) {
+                            if (unitData == TACmiSchemaHandler.NULL_MARKER) {
                                 // no UoM mappable - just send value
                                 channelType = "Number";
                                 unit = null;
                                 state = new DecimalType(bd);
-                            } else if (unitData == taCmiSchemaHandler.SPECIAL_MARKER) {
+                            } else if (unitData == TACmiSchemaHandler.SPECIAL_MARKER) {
                                 // special handling for unknown UoM
                                 if ("Imp".equals(unitStr)) { // Number of Pulses
                                     // impulses - no idea how to map this to something useful here?

bundles/org.openhab.binding.tacmi/src/main/java/org/openhab/binding/tacmi/internal/schema/ChangerX2Parser.java

@@ -102,7 +102,7 @@ public class ChangerX2Parser extends AbstractSimpleMarkupHandler {
             this.optionFieldName = attributes == null ? null : attributes.get("name");
         } else if ((this.parserState == ParserState.INIT || this.parserState == ParserState.INPUT)
                 && "br".equals(elementName)) {
-            // ignored
+            return; // ignored
         } else if ((this.parserState == ParserState.INIT || this.parserState == ParserState.INPUT)
                 && "input".equals(elementName) && "changeto".equals(id)) {
             this.parserState = ParserState.INPUT_DATA;
@@ -171,7 +171,6 @@ public class ChangerX2Parser extends AbstractSimpleMarkupHandler {
                     }
                     this.options.put(ChangerX2Entry.TIME_PERIOD_PARTS, timeParts);
                 } else {
-
                     logger.warn("Error parsing options for {}: Unhandled input field in {}:{}: {}", channelName, line,
                             col, attributes);
                 }
@@ -218,7 +217,7 @@ public class ChangerX2Parser extends AbstractSimpleMarkupHandler {
                 }
             }
         } else if (this.parserState == ParserState.INPUT && "span".equals(elementName)) {
-            // span's are ignored...
+            return; // span's are ignored...
         } else {
             logger.debug("Error parsing options for {}: Unexpected CloseElement in {}:{}: {}", channelName, line, col,
                     elementName);
@@ -275,10 +274,11 @@ public class ChangerX2Parser extends AbstractSimpleMarkupHandler {
                 sb.append(buffer, offset, len);
             }
         } else if (this.parserState == ParserState.INIT && len == 1 && buffer[offset] == '\n') {
-            // single newline - ignore/drop it...
+            return; // single newline - ignore/drop it...
         } else if (this.parserState == ParserState.INPUT) {
             // this is a label next to the value input field - we currently have no use for it so
             // it's dropped...
+            return;
         } else {
             logger.debug("Error parsing options for {}: Unexpected Text {}:{}: (ctx: {} len: {}) '{}' ",
                     this.channelName, line, col, this.parserState, len, new String(buffer, offset, len));

bundles/org.openhab.binding.tacmi/src/main/java/org/openhab/binding/tacmi/internal/schema/TACmiSchemaHandler.java

@@ -90,9 +90,9 @@ public class TACmiSchemaHandler extends BaseThingHandler {
     // this is the units lookup cache.
     protected final Map<String, UnitAndType> unitsCache = new ConcurrentHashMap<>();
     // marks an entry with known un-resolveable unit
-    protected final UnitAndType NULL_MARKER = new UnitAndType(Units.ONE, "");
+    protected static final UnitAndType NULL_MARKER = new UnitAndType(Units.ONE, "");
     // marks an entry with special handling - i.e. 'Imp'
-    protected final UnitAndType SPECIAL_MARKER = new UnitAndType(Units.ONE, "s");
+    protected static final UnitAndType SPECIAL_MARKER = new UnitAndType(Units.ONE, "s");
 
     public TACmiSchemaHandler(final Thing thing, final HttpClient httpClient,
             final TACmiChannelTypeProvider channelTypeProvider) {

bundles/org.openhab.voice.whisperstt/README.md

@@ -5,6 +5,8 @@ It also uses [libfvad](https://github.com/dpirch/libfvad) for voice activity det
 
 [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) is a high-optimized lightweight c++ implementation of [whisper](https://github.com/openai/whisper) that allows to easily integrate it in different platforms and applications.
 
+Alternatively, if you do not want to perform speech-to-text on the computer hosting openHAB, this add-on can consume an OpenAI/Whisper compatible transcription API.
+
 Whisper enables speech recognition for multiple languages and dialects:
 
 english, chinese, german, spanish, russian, korean, french, japanese, portuguese, turkish, polish, catalan, dutch, arabic, swedish,
@@ -15,9 +17,11 @@ marathi, punjabi, sinhala, khmer, shona, yoruba, somali, afrikaans, occitan, geo
 uzbek, faroese, haitian, pashto, turkmen, nynorsk, maltese, sanskrit, luxembourgish, myanmar, tibetan, tagalog, malagasy, assamese, tatar, lingala,
 hausa, bashkir, javanese and sundanese.
 
-## Supported platforms
+## Local mode (offline)
 
-This add-on uses some native binaries to work.
+### Supported platforms
+
+This add-on uses some native binaries to work when performing offline recognition.
 You can find here the used [whisper.cpp Java wrapper](https://github.com/GiviMAD/whisper-jni) and [libfvad Java wrapper](https://github.com/GiviMAD/libfvad-jni).
 
 The following platforms are supported:
@@ -28,7 +32,7 @@ The following platforms are supported:
 
 The native binaries for those platforms are included in this add-on provided with the openHAB distribution.
 
-## CPU compatibility
+### CPU compatibility
 
 To use this binding it's recommended to use a device at least as powerful as the RaspberryPI 5 with a modern CPU.
 The execution times on Raspberry PI 4 are x2, so just the tiny model can be run on under 5 seconds.
@@ -40,18 +44,18 @@ You can check those flags on Windows using a program like `CPU-Z`.
 If you are going to use the binding in a `arm64` host the CPU should support the flags: `fphp`.
 You can check those flags on linux using the terminal with `lscpu`.
 
-## Transcription time
+### Transcription time
 
 On a Raspberry PI 5, the approximate transcription times are:
 
 | model      | exec time |
-| ---------- | --------: |
+|------------|----------:|
 | tiny.bin   |      1.5s |
 | base.bin   |        3s |
 | small.bin  |      8.5s |
 | medium.bin |       17s |
 
-## Configuring the model
+### Configuring the model
 
 Before you can use this service you should configure your model.
 
@@ -64,7 +68,7 @@ You should place the downloaded .bin model in '\<openHAB userdata\>/whisper/' so
 
 Remember to check that you have enough RAM to load the model, estimated RAM consumption can be checked on the huggingface link.
 
-## Using alternative whisper.cpp library
+### Using alternative whisper.cpp library
 
 It's possible to use your own build of the whisper.cpp shared library with this add-on.
 
@@ -76,7 +80,7 @@ In the [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) README you can fi
 
 Note: You need to restart openHAB to reload the library.
 
-## Grammar
+### Grammar
 
 The whisper.cpp library allows to define a grammar to alter the transcription results without fine-tuning the model.
 
@@ -99,6 +103,14 @@ tv_channel ::= ("set ")? "tv channel to " [0-9]+
 
 You can provide the grammar and enable its usage using the binding configuration.
 
+## API mode
+
+You can also use this add-on with a remote API that is compatible with the 'transcription' API from OpenAI. Online services exposing such an API may require an API key (paid services, such as OpenAI).
+
+You can host you own compatible service elsewhere on your network, with third-party software such as faster-whisper-server.
+
+Please note that API mode also uses libvfad for voice activity detection, and that grammar parameters are not available.   
+
 ## Configuration
 
 Use your favorite configuration UI to edit the Whisper settings:
@@ -107,6 +119,7 @@ Use your favorite configuration UI to edit the Whisper settings:
 
 General options.
 
+- **Mode : LOCAL or API** - Choose either local computation or remote API use.
 - **Model Name** - Model name. The 'ggml-' prefix and '.bin' extension are optional here but required on the filename. (ex: tiny.en -> ggml-tiny.en.bin)
 - **Preload Model** - Keep whisper model loaded.
 - **Single Utterance Mode** - When enabled recognition stops listening after a single utterance.
@@ -139,6 +152,13 @@ Configure whisper options.
 - **Initial Prompt** - Initial prompt for whisper.
 - **OpenVINO Device** - Initialize OpenVINO encoder. (built-in binaries do not support OpenVINO, this has no effect)
 - **Use GPU** - Enables GPU usage. (built-in binaries do not support GPU usage, this has no effect)
+- **Language** - If specified, speed up recognition by avoiding auto-detection. Default to system locale.
+
+### API Configuration
+
+- **API key** - Optional use of an API key for online services requiring it.
+- **API url** - You may use your own service and define its URL here. Default set to OpenAI transcription API.
+- **API model name** - Your hosted service may have other models. Default to OpenAI only model 'whisper-1'.
 
 ### Grammar Configuration
 
@@ -199,7 +219,9 @@ In case you would like to set up the service via a text file, create a new file
 Its contents should look similar to:
 
 ```ini
+org.openhab.voice.whisperstt:mode=LOCAL
 org.openhab.voice.whisperstt:modelName=tiny
+org.openhab.voice.whisperstt:language=en
 org.openhab.voice.whisperstt:initSilenceSeconds=0.3
 org.openhab.voice.whisperstt:removeSilence=true
 org.openhab.voice.whisperstt:stepSeconds=0.3
@@ -229,6 +251,9 @@ org.openhab.voice.whisperstt:useGPU=false
 org.openhab.voice.whisperstt:useGrammar=false
 org.openhab.voice.whisperstt:grammarPenalty=80.0
 org.openhab.voice.whisperstt:grammarLines=
+org.openhab.voice.whisperstt:apiKey=mykeyaaaa
+org.openhab.voice.whisperstt:apiUrl=https://api.openai.com/v1/audio/transcriptions
+org.openhab.voice.whisperstt:apiModelName=whisper-1
 ```
 
 ### Default Speech-to-Text Configuration

bundles/org.openhab.voice.whisperstt/src/main/java/org/openhab/voice/whisperstt/internal/WhisperSTTConfiguration.java

@@ -146,4 +146,29 @@ public class WhisperSTTConfiguration {
      * Print whisper.cpp library logs as binding debug logs.
      */
     public boolean enableWhisperLog;
+    /**
+     * local to use embedded whisper or openaiapi to use an external API
+     */
+    public Mode mode = Mode.LOCAL;
+    /**
+     * If mode set to openaiapi, then use this URL
+     */
+    public String apiUrl = "https://api.openai.com/v1/audio/transcriptions";
+    /**
+     * if mode set to openaiapi, use this api key to access apiUrl
+     */
+    public String apiKey = "";
+    /**
+     * If specified, speed up recognition by avoiding auto-detection
+     */
+    public String language = "";
+    /**
+     * Model name (API only)
+     */
+    public String apiModelName = "whisper-1";
+
+    public static enum Mode {
+        LOCAL,
+        API;
+    }
 }

bundles/org.openhab.voice.whisperstt/src/main/java/org/openhab/voice/whisperstt/internal/WhisperSTTService.java

@@ -12,12 +12,10 @@
  */
 package org.openhab.voice.whisperstt.internal;
 
-import static org.openhab.voice.whisperstt.internal.WhisperSTTConstants.SERVICE_CATEGORY;
+import static org.openhab.voice.whisperstt.internal.WhisperSTTConstants.*;
-import static org.openhab.voice.whisperstt.internal.WhisperSTTConstants.SERVICE_ID;
-import static org.openhab.voice.whisperstt.internal.WhisperSTTConstants.SERVICE_NAME;
-import static org.openhab.voice.whisperstt.internal.WhisperSTTConstants.SERVICE_PID;
 
 import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.nio.ByteBuffer;
@@ -32,7 +30,9 @@ import java.util.Date;
 import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
+import java.util.concurrent.ExecutionException;
 import java.util.concurrent.ScheduledExecutorService;
+import java.util.concurrent.TimeoutException;
 import java.util.concurrent.atomic.AtomicBoolean;
 
 import javax.sound.sampled.AudioFileFormat;
@@ -41,6 +41,13 @@ import javax.sound.sampled.AudioSystem;
 
 import org.eclipse.jdt.annotation.NonNullByDefault;
 import org.eclipse.jdt.annotation.Nullable;
+import org.eclipse.jetty.client.HttpClient;
+import org.eclipse.jetty.client.api.ContentResponse;
+import org.eclipse.jetty.client.api.Request;
+import org.eclipse.jetty.client.util.InputStreamContentProvider;
+import org.eclipse.jetty.client.util.MultiPartContentProvider;
+import org.eclipse.jetty.client.util.StringContentProvider;
+import org.eclipse.jetty.http.HttpMethod;
 import org.openhab.core.OpenHAB;
 import org.openhab.core.audio.AudioFormat;
 import org.openhab.core.audio.AudioStream;
@@ -48,6 +55,7 @@ import org.openhab.core.audio.utils.AudioWaveUtils;
 import org.openhab.core.common.ThreadPoolManager;
 import org.openhab.core.config.core.ConfigurableService;
 import org.openhab.core.config.core.Configuration;
+import org.openhab.core.io.net.http.HttpClientFactory;
 import org.openhab.core.io.rest.LocaleService;
 import org.openhab.core.voice.RecognitionStartEvent;
 import org.openhab.core.voice.RecognitionStopEvent;
@@ -57,6 +65,7 @@ import org.openhab.core.voice.STTService;
 import org.openhab.core.voice.STTServiceHandle;
 import org.openhab.core.voice.SpeechRecognitionErrorEvent;
 import org.openhab.core.voice.SpeechRecognitionEvent;
+import org.openhab.voice.whisperstt.internal.WhisperSTTConfiguration.Mode;
 import org.openhab.voice.whisperstt.internal.utils.VAD;
 import org.osgi.framework.Constants;
 import org.osgi.service.component.annotations.Activate;
@@ -96,10 +105,13 @@ public class WhisperSTTService implements STTService {
     private @Nullable WhisperContext context;
     private @Nullable WhisperGrammar grammar;
     private @Nullable WhisperJNI whisper;
+    private boolean isWhisperLibAlreadyLoaded = false;
+    private final HttpClientFactory httpClientFactory;
 
     @Activate
-    public WhisperSTTService(@Reference LocaleService localeService) {
+    public WhisperSTTService(@Reference LocaleService localeService, @Reference HttpClientFactory httpClientFactory) {
         this.localeService = localeService;
+        this.httpClientFactory = httpClientFactory;
     }
 
     @Activate
@@ -108,7 +120,8 @@ public class WhisperSTTService implements STTService {
             if (!Files.exists(WHISPER_FOLDER)) {
                 Files.createDirectory(WHISPER_FOLDER);
             }
-            WhisperJNI.loadLibrary(getLoadOptions());
+            this.config = new Configuration(config).as(WhisperSTTConfiguration.class);
+            loadWhisperLibraryIfNeeded();
             VoiceActivityDetector.loadLibrary();
             whisper = new WhisperJNI();
         } catch (IOException | RuntimeException e) {
@@ -117,6 +130,13 @@ public class WhisperSTTService implements STTService {
         configChange(config);
     }
 
+    private void loadWhisperLibraryIfNeeded() throws IOException {
+        if (config.mode == Mode.LOCAL && !isWhisperLibAlreadyLoaded) {
+            WhisperJNI.loadLibrary(getLoadOptions());
+            isWhisperLibAlreadyLoaded = true;
+        }
+    }
+
     private WhisperJNI.LoadOptions getLoadOptions() {
         Path libFolder = Paths.get("/usr/local/lib");
         Path libFolderWin = Paths.get("/Windows/System32");
@@ -167,14 +187,27 @@ public class WhisperSTTService implements STTService {
 
     private void configChange(Map<String, Object> config) {
         this.config = new Configuration(config).as(WhisperSTTConfiguration.class);
-        WhisperJNI.setLibraryLogger(this.config.enableWhisperLog ? this::onWhisperLog : null);
         WhisperGrammar grammar = this.grammar;
         if (grammar != null) {
             grammar.close();
             this.grammar = null;
         }
+
+        // API mode
+        if (this.config.mode == Mode.API) {
+            try {
+                unloadContext();
+            } catch (IOException e) {
+                logger.warn("IOException unloading model: {}", e.getMessage());
+            }
+            return;
+        }
+
+        // Local mode
         WhisperJNI whisper;
         try {
+            loadWhisperLibraryIfNeeded();
+            WhisperJNI.setLibraryLogger(this.config.enableWhisperLog ? this::onWhisperLog : null);
             whisper = getWhisper();
         } catch (IOException ignored) {
             logger.warn("library not loaded, the add-on will not work");
@@ -228,9 +261,17 @@ public class WhisperSTTService implements STTService {
 
     @Override
     public Set<Locale> getSupportedLocales() {
-        // as it is not possible to determine the language of the model that was downloaded and setup by the user, it is
+        // Attempt to create a locale from the configured language
-        // assumed the language of the model is matching the locale of the openHAB server
+        String language = config.language;
-        return Set.of(localeService.getLocale(null));
+        Locale modelLocale = localeService.getLocale(null);
+        if (!language.isBlank()) {
+            try {
+                modelLocale = Locale.forLanguageTag(language);
+            } catch (IllegalArgumentException e) {
+                logger.warn("Invalid language '{}', defaulting to server locale", language);
+            }
+        }
+        return Set.of(modelLocale);
     }
 
     @Override
@@ -246,33 +287,18 @@ public class WhisperSTTService implements STTService {
     public STTServiceHandle recognize(STTListener sttListener, AudioStream audioStream, Locale locale, Set<String> set)
             throws STTException {
         AtomicBoolean aborted = new AtomicBoolean(false);
-        WhisperContext ctx = null;
-        WhisperState state = null;
         try {
-            var whisper = getWhisper();
-            ctx = getContext();
-            logger.debug("Creating whisper state...");
-            state = whisper.initState(ctx);
-            logger.debug("Whisper state created");
             logger.debug("Creating VAD instance...");
-            final int nSamplesStep = (int) (config.stepSeconds * (float) WHISPER_SAMPLE_RATE);
+            final int nSamplesStep = (int) (config.stepSeconds * WHISPER_SAMPLE_RATE);
             VAD vad = new VAD(VoiceActivityDetector.Mode.valueOf(config.vadMode), WHISPER_SAMPLE_RATE, nSamplesStep,
                     config.vadStep, config.vadSensitivity);
             logger.debug("VAD instance created");
             sttListener.sttEventReceived(new RecognitionStartEvent());
-            backgroundRecognize(whisper, ctx, state, nSamplesStep, locale, sttListener, audioStream, vad, aborted);
+            backgroundRecognize(nSamplesStep, locale, sttListener, audioStream, vad, aborted);
         } catch (IOException e) {
-            if (ctx != null && !config.preloadModel) {
-                ctx.close();
-            }
-            if (state != null) {
-                state.close();
-            }
             throw new STTException("Exception during initialization", e);
         }
-        return () -> {
+        return () -> aborted.set(true);
-            aborted.set(true);
-        };
     }
 
     private WhisperJNI getWhisper() throws IOException {
@@ -339,9 +365,8 @@ public class WhisperSTTService implements STTService {
         }
     }
 
-    private void backgroundRecognize(WhisperJNI whisper, WhisperContext ctx, WhisperState state, final int nSamplesStep,
+    private void backgroundRecognize(final int nSamplesStep, Locale locale, STTListener sttListener,
-            Locale locale, STTListener sttListener, AudioStream audioStream, VAD vad, AtomicBoolean aborted) {
+            AudioStream audioStream, VAD vad, AtomicBoolean aborted) {
-        var releaseContext = !config.preloadModel;
         final int nSamplesMax = config.maxSeconds * WHISPER_SAMPLE_RATE;
         final int nSamplesMin = (int) (config.minSeconds * (float) WHISPER_SAMPLE_RATE);
         final int nInitSilenceSamples = (int) (config.initSilenceSeconds * (float) WHISPER_SAMPLE_RATE);
@@ -353,21 +378,17 @@ public class WhisperSTTService implements STTService {
         logger.debug("Max silence samples {}", nMaxSilenceSamples);
         // used to store the step samples in libfvad wanted format 16-bit int
         final short[] stepAudioSamples = new short[nSamplesStep];
-        // used to store the full samples in whisper wanted format 32-bit float
+        // used to store the full retained samples for whisper
-        final float[] audioSamples = new float[nSamplesMax];
+        final short[] audioSamples = new short[nSamplesMax];
         executor.submit(() -> {
             int audioSamplesOffset = 0;
             int silenceSamplesCounter = 0;
             int nProcessedSamples = 0;
-            int numBytesRead;
             boolean voiceDetected = false;
             String transcription = "";
-            String tempTranscription = "";
-            VAD.@Nullable VADResult lastVADResult;
             VAD.@Nullable VADResult firstConsecutiveSilenceVADResult = null;
             try {
-                try (state; //
+                try (audioStream; //
-                        audioStream; //
                         vad) {
                     if (AudioFormat.CONTAINER_WAVE.equals(audioStream.getFormat().getContainer())) {
                         AudioWaveUtils.removeFMT(audioStream);
@@ -376,10 +397,9 @@ public class WhisperSTTService implements STTService {
                             .order(ByteOrder.LITTLE_ENDIAN);
                     // init remaining to full capacity
                     int remaining = captureBuffer.capacity();
-                    WhisperFullParams params = getWhisperFullParams(ctx, locale);
                     while (!aborted.get()) {
                         // read until no remaining so we get the complete step samples
-                        numBytesRead = audioStream.read(captureBuffer.array(), captureBuffer.capacity() - remaining,
+                        int numBytesRead = audioStream.read(captureBuffer.array(), captureBuffer.capacity() - remaining,
                                 remaining);
                         if (aborted.get() || numBytesRead == -1) {
                             break;
@@ -395,17 +415,15 @@ public class WhisperSTTService implements STTService {
                         while (shortBuffer.hasRemaining()) {
                             var position = shortBuffer.position();
                             short i16BitSample = shortBuffer.get();
-                            float f32BitSample = Float.min(1f,
-                                    Float.max((float) i16BitSample / ((float) Short.MAX_VALUE), -1f));
                             stepAudioSamples[position] = i16BitSample;
-                            audioSamples[audioSamplesOffset++] = f32BitSample;
+                            audioSamples[audioSamplesOffset++] = i16BitSample;
                             nProcessedSamples++;
                         }
                         // run vad
                         if (nProcessedSamples + nSamplesStep > nSamplesMax - nSamplesStep) {
                             logger.debug("VAD: Skipping, max length reached");
                         } else {
-                            lastVADResult = vad.analyze(stepAudioSamples);
+                            VAD.@Nullable VADResult lastVADResult = vad.analyze(stepAudioSamples);
                             if (lastVADResult.isVoice()) {
                                 voiceDetected = true;
                                 logger.debug("VAD: voice detected");
@@ -484,43 +502,26 @@ public class WhisperSTTService implements STTService {
                                 }
                             }
                         }
-                        // run whisper
+                        // run whisper, either locally or by remote API
-                        logger.debug("running whisper with {} seconds of audio...",
+                        String tempTranscription = (switch (config.mode) {
-                                Math.round((((float) audioSamplesOffset) / (float) WHISPER_SAMPLE_RATE) * 100f) / 100f);
+                            case LOCAL -> recognizeLocal(audioSamplesOffset, audioSamples, locale.getLanguage());
-                        long execStartTime = System.currentTimeMillis();
+                            case API -> recognizeAPI(audioSamplesOffset, audioSamples, locale.getLanguage());
-                        var result = whisper.fullWithState(ctx, state, params, audioSamples, audioSamplesOffset);
+                        });
-                        logger.debug("whisper ended in {}ms with result code {}",
+
-                                System.currentTimeMillis() - execStartTime, result);
+                        if (tempTranscription != null && !tempTranscription.isBlank()) {
-                        // process result
-                        if (result != 0) {
-                            emitSpeechRecognitionError(sttListener);
-                            break;
-                        }
-                        int nSegments = whisper.fullNSegmentsFromState(state);
-                        logger.debug("Available transcription segments {}", nSegments);
-                        if (nSegments == 1) {
-                            tempTranscription = whisper.fullGetSegmentTextFromState(state, 0);
                             if (config.createWAVRecord) {
                                 createAudioFile(audioSamples, audioSamplesOffset, tempTranscription,
                                         locale.getLanguage());
                             }
+                            transcription += tempTranscription;
                             if (config.singleUtteranceMode) {
                                 logger.debug("single utterance mode, ending transcription");
-                                transcription = tempTranscription;
                                 break;
-                            } else {
-                                // start a new transcription segment
-                                transcription += tempTranscription;
-                                tempTranscription = "";
                             }
-                        } else if (nSegments == 0 && config.singleUtteranceMode) {
+                        } else {
-                            logger.debug("Single utterance mode and no results, ending transcription");
-                            break;
-                        } else if (nSegments > 1) {
-                            // non reachable
-                            logger.warn("Whisper should be configured in single segment mode {}", nSegments);
                             break;
                         }
+
                         // reset state to start with next segment
                         voiceDetected = false;
                         silenceSamplesCounter = 0;
@@ -528,10 +529,6 @@ public class WhisperSTTService implements STTService {
                         logger.debug("Partial transcription: {}", tempTranscription);
                         logger.debug("Transcription: {}", transcription);
                     }
-                } finally {
-                    if (releaseContext) {
-                        ctx.close();
-                    }
                 }
                 // emit result
                 if (!aborted.get()) {
@@ -543,7 +540,7 @@ public class WhisperSTTService implements STTService {
                         emitSpeechRecognitionNoResultsError(sttListener);
                     }
                 }
-            } catch (IOException e) {
+            } catch (STTException | IOException e) {
                 logger.warn("Error running speech to text: {}", e.getMessage());
                 emitSpeechRecognitionError(sttListener);
             } catch (UnsatisfiedLinkError e) {
@@ -553,7 +550,119 @@ public class WhisperSTTService implements STTService {
         });
     }
 
-    private WhisperFullParams getWhisperFullParams(WhisperContext context, Locale locale) throws IOException {
+    @Nullable
+    private String recognizeLocal(int audioSamplesOffset, short[] audioSamples, String language) throws STTException {
+        logger.debug("running whisper with {} seconds of audio...",
+                Math.round((((float) audioSamplesOffset) / (float) WHISPER_SAMPLE_RATE) * 100f) / 100f);
+        var releaseContext = !config.preloadModel;
+
+        WhisperJNI whisper = null;
+        WhisperContext ctx = null;
+        WhisperState state = null;
+        try {
+            whisper = getWhisper();
+            ctx = getContext();
+            logger.debug("Creating whisper state...");
+            state = whisper.initState(ctx);
+            logger.debug("Whisper state created");
+            WhisperFullParams params = getWhisperFullParams(ctx, language);
+
+            // convert to local whisper format (float)
+            float[] floatArray = new float[audioSamples.length];
+            for (int i = 0; i < audioSamples.length; i++) {
+                floatArray[i] = Float.min(1f, Float.max((float) audioSamples[i] / ((float) Short.MAX_VALUE), -1f));
+            }
+
+            long execStartTime = System.currentTimeMillis();
+            var result = whisper.fullWithState(ctx, state, params, floatArray, audioSamplesOffset);
+            logger.debug("whisper ended in {}ms with result code {}", System.currentTimeMillis() - execStartTime,
+                    result);
+            // process result
+            if (result != 0) {
+                throw new STTException("Cannot use whisper locally, result code: " + result);
+            }
+            int nSegments = whisper.fullNSegmentsFromState(state);
+            logger.debug("Available transcription segments {}", nSegments);
+            if (nSegments == 1) {
+                return whisper.fullGetSegmentTextFromState(state, 0);
+            } else if (nSegments == 0 && config.singleUtteranceMode) {
+                logger.debug("Single utterance mode and no results, ending transcription");
+                return null;
+            } else {
+                // non reachable
+                logger.warn("Whisper should be configured in single segment mode {}", nSegments);
+                return null;
+            }
+        } catch (IOException e) {
+            if (state != null) {
+                state.close();
+            }
+            throw new STTException("Cannot use whisper locally", e);
+        } finally {
+            if (releaseContext && ctx != null) {
+                ctx.close();
+            }
+        }
+    }
+
+    private String recognizeAPI(int audioSamplesOffset, short[] audioStream, String language) throws STTException {
+        // convert to byte array, Each short has 2 bytes
+        int size = audioSamplesOffset * 2;
+        ByteBuffer byteArrayBuffer = ByteBuffer.allocate(size).order(ByteOrder.LITTLE_ENDIAN);
+        for (int i = 0; i < audioSamplesOffset; i++) {
+            byteArrayBuffer.putShort(audioStream[i]);
+        }
+        javax.sound.sampled.AudioFormat jAudioFormat = new javax.sound.sampled.AudioFormat(
+                javax.sound.sampled.AudioFormat.Encoding.PCM_SIGNED, WHISPER_SAMPLE_RATE, 16, 1, 2, WHISPER_SAMPLE_RATE,
+                false);
+        byte[] byteArray = byteArrayBuffer.array();
+
+        try {
+            AudioInputStream audioInputStream = new AudioInputStream(new ByteArrayInputStream(byteArray), jAudioFormat,
+                    audioSamplesOffset);
+
+            // write stream as a WAV file, in a byte array stream :
+            ByteArrayInputStream byteArrayInputStream = null;
+            try (ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+                AudioSystem.write(audioInputStream, AudioFileFormat.Type.WAVE, baos);
+                byteArrayInputStream = new ByteArrayInputStream(baos.toByteArray());
+            }
+
+            // prepare HTTP request
+            HttpClient commonHttpClient = httpClientFactory.getCommonHttpClient();
+            MultiPartContentProvider multiPartContentProvider = new MultiPartContentProvider();
+            multiPartContentProvider.addFilePart("file", "audio.wav",
+                    new InputStreamContentProvider(byteArrayInputStream), null);
+            multiPartContentProvider.addFieldPart("model", new StringContentProvider(this.config.apiModelName), null);
+            multiPartContentProvider.addFieldPart("response_format", new StringContentProvider("text"), null);
+            multiPartContentProvider.addFieldPart("temperature",
+                    new StringContentProvider(Float.toString(this.config.temperature)), null);
+            if (!language.isBlank()) {
+                multiPartContentProvider.addFieldPart("language", new StringContentProvider(language), null);
+            }
+            Request request = commonHttpClient.newRequest(config.apiUrl).method(HttpMethod.POST)
+                    .content(multiPartContentProvider);
+            if (!config.apiKey.isBlank()) {
+                request = request.header("Authorization", "Bearer " + config.apiKey);
+            }
+            // execute the request
+            ContentResponse response = request.send();
+
+            // check the HTTP status code from the response
+            int statusCode = response.getStatus();
+            if (statusCode < 200 || statusCode >= 300) {
+                logger.debug("HTTP error: Received status code {}, full error is {}", statusCode,
+                        response.getContentAsString());
+                throw new STTException("Failed to retrieve transcription: HTTP status code " + statusCode);
+            }
+            return response.getContentAsString();
+
+        } catch (InterruptedException | TimeoutException | ExecutionException | IOException e) {
+            throw new STTException("Exception during attempt to get speech recognition result from api", e);
+        }
+    }
+
+    private WhisperFullParams getWhisperFullParams(WhisperContext context, String language) throws IOException {
         WhisperSamplingStrategy strategy = WhisperSamplingStrategy.valueOf(config.samplingStrategy);
         var params = new WhisperFullParams(strategy);
         params.temperature = config.temperature;
@@ -570,7 +679,7 @@ public class WhisperSTTService implements STTService {
             params.grammarPenalty = config.grammarPenalty;
         }
         // there is no single language models other than the english ones
-        params.language = getWhisper().isMultilingual(context) ? locale.getLanguage() : "en";
+        params.language = getWhisper().isMultilingual(context) ? language : "en";
         // implementation assumes this options
         params.translate = false;
         params.detectLanguage = false;
@@ -605,7 +714,7 @@ public class WhisperSTTService implements STTService {
         }
     }
 
-    private void createAudioFile(float[] samples, int size, String transcription, String language) {
+    private void createAudioFile(short[] samples, int size, String transcription, String language) {
         createSamplesDir();
         javax.sound.sampled.AudioFormat jAudioFormat;
         ByteBuffer byteBuffer;
@@ -615,7 +724,7 @@ public class WhisperSTTService implements STTService {
                     WHISPER_SAMPLE_RATE, 16, 1, 2, WHISPER_SAMPLE_RATE, false);
             byteBuffer = ByteBuffer.allocate(size * 2).order(ByteOrder.LITTLE_ENDIAN);
             for (int i = 0; i < size; i++) {
-                byteBuffer.putShort((short) (samples[i] * (float) Short.MAX_VALUE));
+                byteBuffer.putShort(samples[i]);
             }
         } else {
             logger.debug("Saving audio file with sample format f32");
@@ -623,7 +732,7 @@ public class WhisperSTTService implements STTService {
                     WHISPER_SAMPLE_RATE, 32, 1, 4, WHISPER_SAMPLE_RATE, false);
             byteBuffer = ByteBuffer.allocate(size * 4).order(ByteOrder.LITTLE_ENDIAN);
             for (int i = 0; i < size; i++) {
-                byteBuffer.putFloat(samples[i]);
+                byteBuffer.putFloat(Float.min(1f, Float.max((float) samples[i] / ((float) Short.MAX_VALUE), -1f)));
             }
         }
         AudioInputStream audioInputStreamTemp = new AudioInputStream(new ByteArrayInputStream(byteBuffer.array()),

bundles/org.openhab.voice.whisperstt/src/main/resources/OH-INF/config/config.xml

@@ -11,7 +11,7 @@
 		</parameter-group>
 		<parameter-group name="vad">
 			<label>Voice Activity Detection</label>
-			<description>Configure the VAD mechanisim used to isolate single phrases to feed whisper with.</description>
+			<description>Configure the VAD mechanism used to isolate single phrases to feed whisper with.</description>
 		</parameter-group>
 		<parameter-group name="whisper">
 			<label>Whisper Options</label>
@@ -19,7 +19,7 @@
 		</parameter-group>
 		<parameter-group name="grammar">
 			<label>Grammar</label>
-			<description>Define a grammar to improve transcrptions.</description>
+			<description>Define a grammar to improve transcriptions.</description>
 		</parameter-group>
 		<parameter-group name="messages">
 			<label>Info Messages</label>
@@ -30,9 +30,27 @@
 			<description>Options added for developers.</description>
 			<advanced>true</advanced>
 		</parameter-group>
+		<parameter-group name="openaiapi">
+			<label>API Configuration Options</label>
+			<description>Configure OpenAI compatible API, if you don't want to use the local model.</description>
+		</parameter-group>
+		<parameter name="mode" type="text" groupName="stt">
+			<label>Local Mode Or API</label>
+			<description>Use the local model or the OpenAI compatible API.</description>
+			<default>LOCAL</default>
+			<options>
+				<option value="LOCAL">Local</option>
+				<option value="API">OpenAI API</option>
+			</options>
+		</parameter>
 		<parameter name="modelName" type="text" groupName="stt" required="true">
-			<label>Model Name</label>
+			<label>Local Model Name</label>
-			<description>Model name without extension.</description>
+			<description>Model name without extension. Local mode only.</description>
+		</parameter>
+		<parameter name="language" type="text" groupName="whisper">
+			<label>Language</label>
+			<description>If specified, speed up recognition by avoiding auto-detection. Default to system locale.</description>
+			<default></default>
 		</parameter>
 		<parameter name="preloadModel" type="boolean" groupName="stt">
 			<label>Preload Model</label>
@@ -225,5 +243,20 @@
 			<default>false</default>
 			<advanced>true</advanced>
 		</parameter>
+		<parameter name="apiKey" type="text" groupName="openaiapi">
+			<label>API Key</label>
+			<description>Key to access the API</description>
+			<default></default>
+		</parameter>
+		<parameter name="apiUrl" type="text" groupName="openaiapi">
+			<label>API Url</label>
+			<description>OpenAI compatible API URL. Default to OpenAI transcription service.</description>
+			<default>https://api.openai.com/v1/audio/transcriptions</default>
+		</parameter>
+		<parameter name="apiModelName" type="text" groupName="openaiapi">
+			<label>API Model</label>
+			<description>Model name to use (API only). Default to OpenAI only available model (whisper-1).</description>
+			<default>whisper-1</default>
+		</parameter>
 	</config-description>
 </config-description:config-descriptions>

bundles/org.openhab.voice.whisperstt/src/main/resources/OH-INF/i18n/whisperstt.properties

@@ -3,6 +3,12 @@
 addon.whisperstt.name = Whisper Speech-to-Text
 addon.whisperstt.description = Whisper STT Service uses the whisper.cpp library to transcript audio data to text.
 
+voice.config.whisperstt.apiKey.label = API Key
+voice.config.whisperstt.apiKey.description = Key to access the API
+voice.config.whisperstt.apiModelName.label = API Model
+voice.config.whisperstt.apiModelName.description = Model name to use (API only). Default to OpenAI only available model (whisper-1).
+voice.config.whisperstt.apiUrl.label = API Url
+voice.config.whisperstt.apiUrl.description = OpenAI compatible API URL. Default to OpenAI transcription service.
 voice.config.whisperstt.audioContext.label = Audio Context
 voice.config.whisperstt.audioContext.description = Overwrite the audio context size. (0 to use whisper default context size)
 voice.config.whisperstt.beamSize.label = Beam Size
@@ -24,27 +30,35 @@ voice.config.whisperstt.greedyBestOf.description = Best Of configuration for sam
 voice.config.whisperstt.group.developer.label = Developer
 voice.config.whisperstt.group.developer.description = Options added for developers.
 voice.config.whisperstt.group.grammar.label = Grammar
-voice.config.whisperstt.group.grammar.description = Define a grammar to improve transcrptions.
+voice.config.whisperstt.group.grammar.description = Define a grammar to improve transcriptions.
 voice.config.whisperstt.group.messages.label = Info Messages
 voice.config.whisperstt.group.messages.description = Configure service information messages.
+voice.config.whisperstt.group.openaiapi.label = API Configuration Options
+voice.config.whisperstt.group.openaiapi.description = Configure OpenAI compatible API, if you don't want to use the local model.
 voice.config.whisperstt.group.stt.label = STT Configuration
 voice.config.whisperstt.group.stt.description = Configure Speech to Text.
 voice.config.whisperstt.group.vad.label = Voice Activity Detection
-voice.config.whisperstt.group.vad.description = Configure the VAD mechanisim used to isolate single phrases to feed whisper with.
+voice.config.whisperstt.group.vad.description = Configure the VAD mechanism used to isolate single phrases to feed whisper with.
 voice.config.whisperstt.group.whisper.label = Whisper Options
 voice.config.whisperstt.group.whisper.description = Configure the whisper.cpp transcription options.
 voice.config.whisperstt.initSilenceSeconds.label = Initial Silence Seconds
 voice.config.whisperstt.initSilenceSeconds.description = Max initial seconds of silence to discard transcription.
 voice.config.whisperstt.initialPrompt.label = Initial Prompt
 voice.config.whisperstt.initialPrompt.description = Initial prompt to feed whisper with.
+voice.config.whisperstt.language.label = Language
+voice.config.whisperstt.language.description = If specified, speed up recognition by avoiding auto-detection. Default to system locale.
 voice.config.whisperstt.maxSeconds.label = Max Transcription Seconds
 voice.config.whisperstt.maxSeconds.description = Seconds to force transcription before silence detection.
 voice.config.whisperstt.maxSilenceSeconds.label = Max Silence Seconds
 voice.config.whisperstt.maxSilenceSeconds.description = Seconds of silence to trigger transcription.
 voice.config.whisperstt.minSeconds.label = Min Transcription Seconds
 voice.config.whisperstt.minSeconds.description = Min transcription seconds passed to whisper.
-voice.config.whisperstt.modelName.label = Model Name
+voice.config.whisperstt.mode.label = Local Mode Or API
-voice.config.whisperstt.modelName.description = Model name without extension.
+voice.config.whisperstt.mode.description = Use the local model or the OpenAI compatible API.
+voice.config.whisperstt.mode.option.LOCAL = Local
+voice.config.whisperstt.mode.option.API = OpenAI API
+voice.config.whisperstt.modelName.label = Local Model Name
+voice.config.whisperstt.modelName.description = Model name without extension. Local mode only.
 voice.config.whisperstt.openvinoDevice.label = OpenVINO Device
 voice.config.whisperstt.openvinoDevice.description = Initialize OpenVINO encoder. (built-in binaries do not support OpenVINO, this has no effect)
 voice.config.whisperstt.preloadModel.label = Preload Model

itests/org.openhab.binding.mqtt.homie.tests/src/main/java/org/openhab/binding/mqtt/homie/HomieImplementationTest.java

@@ -165,6 +165,7 @@ public class HomieImplementationTest extends MqttOSGiTest {
                 "Connection " + homieConnection.getClientId() + " not retrieving all topics ");
     }
 
+    @Disabled("https://github.com/openhab/openhab-addons/issues/12667")
     @Test
     public void retrieveOneAttribute() throws Exception {
         WaitForTopicValue watcher = new WaitForTopicValue(homieConnection, DEVICE_TOPIC + "/$homie");

itests/org.openhab.binding.wemo.tests/src/main/java/org/openhab/binding/wemo/internal/handler/test/WemoMakerHandlerOSGiTest.java

@@ -107,6 +107,7 @@ public class WemoMakerHandlerOSGiTest extends GenericWemoOSGiTest {
     }
 
     @Test
+    @Disabled("https://github.com/openhab/openhab-addons/issues/12474")
     public void assertThatThingHandlesREFRESHCommand()
             throws MalformedURLException, URISyntaxException, ValidationException, IOException {
         Command command = RefreshType.REFRESH;