Update SpeechmaticsSTTService to use the python voice SDK

changelog/3225.changed.md

@@ -0,0 +1,15 @@
+- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
+  Smart Turn capabilities, and brings dramatic improvements to latency without
+  any impact on accuracy. Use the `turn_detection_mode` parameter to control the
+  endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
+  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
+  ```python
+    stt = SpeechmaticsSTTService(
+        api_key=os.getenv("SPEECHMATICS_API_KEY"),
+        params=SpeechmaticsSTTService.InputParams(
+            language=Language.EN,
+            turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
+            speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
+        ),
+    )
+  ```

changelog/3225.deprecated.md

@@ -0,0 +1,4 @@
+- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
+  Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
+  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
+  parameter is also deprecated and is inferred from the `turn_detection_mode`.

examples/foundational/07a-interruptible-speechmatics-vad.py

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     4. Text-to-Speech (TTS)
        - Low latency streaming audio synthesis
-       - Multiple voice options available including `sarah`, `theo`, and `megan`
+       - Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
 
     5. Configuration Options
        - `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
@@ -92,10 +92,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
             params=SpeechmaticsSTTService.InputParams(
                 language=Language.EN,
-                enable_vad=True,
+                turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
-                enable_diarization=True,
+                # focus_speakers=["S1"],
-                focus_speakers=["S1"],
-                end_of_utterance_silence_trigger=0.5,
                 speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
                 speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
             ),

examples/foundational/07a-interruptible-speechmatics.py

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     TTS Features:
     - Low latency streaming audio synthesis
-    - Multiple voice options available including `sarah`, `theo`, and `megan`
+    - Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
 
     For more information:
     - STT: https://docs.speechmatics.com/rt-api-ref
@@ -83,8 +83,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
             params=SpeechmaticsSTTService.InputParams(
                 language=Language.EN,
-                enable_diarization=True,
-                end_of_utterance_silence_trigger=0.5,
                 speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
             ),
         )

examples/foundational/13h-speechmatics-transcription.py

@@ -68,7 +68,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("SPEECHMATICS_API_KEY"),
         params=SpeechmaticsSTTService.InputParams(
             language=Language.EN,
-            enable_diarization=True,
             speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
         ),
     )

pyproject.toml

@@ -105,7 +105,7 @@ silero = [ "onnxruntime>=1.20.1,<2" ]
 simli = [ "simli-ai~=1.0.3"]
 soniox = [ "pipecat-ai[websockets-base]" ]
 soundfile = [ "soundfile~=0.13.1" ]
-speechmatics = [ "speechmatics-rt>=0.5.0" ]
+speechmatics = [ "speechmatics-voice[smart]>=0.2.4" ]
 strands = [ "strands-agents>=1.9.1,<2" ]
 tavus=[]
 together = []