Merge pull request #1198 from pipecat-ai/mb/more-whisper-params

Add prompt and temperature args to OpenAI and Groq hosted Whisper STT…

src/pipecat/services/base_whisper.py

@@ -111,6 +111,8 @@ class BaseWhisperSTTService(SegmentedSTTService):
         api_key: Service API key. Defaults to None.
         base_url: Service API base URL. Defaults to None.
         language: Language of the audio input. Defaults to English.
+        prompt: Optional text to guide the model's style or continue a previous segment.
+        temperature: Sampling temperature between 0 and 1. Defaults to 0.0.
         **kwargs: Additional arguments passed to SegmentedSTTService.
     """
 
@@ -121,12 +123,16 @@ class BaseWhisperSTTService(SegmentedSTTService):
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         language: Optional[Language] = Language.EN,
+        prompt: Optional[str] = None,
+        temperature: Optional[float] = None,
         **kwargs,
     ):
         super().__init__(**kwargs)
         self.set_model_name(model)
         self._client = self._create_client(api_key, base_url)
         self._language = self.language_to_service_language(language or Language.EN)
+        self._prompt = prompt
+        self._temperature = temperature
 
     def _create_client(self, api_key: Optional[str], base_url: Optional[str]):
         return AsyncOpenAI(api_key=api_key, base_url=base_url)

src/pipecat/services/groq.py

@@ -54,6 +54,8 @@ class GroqSTTService(BaseWhisperSTTService):
         api_key: Groq API key. Defaults to None.
         base_url: API base URL. Defaults to "https://api.groq.com/openai/v1".
         language: Language of the audio input. Defaults to English.
+        prompt: Optional text to guide the model's style or continue a previous segment.
+        temperature: Optional sampling temperature between 0 and 1. Defaults to 0.0.
         **kwargs: Additional arguments passed to BaseWhisperSTTService.
     """
 
@@ -64,17 +66,35 @@ class GroqSTTService(BaseWhisperSTTService):
         api_key: Optional[str] = None,
         base_url: str = "https://api.groq.com/openai/v1",
         language: Optional[Language] = Language.EN,
+        prompt: Optional[str] = None,
+        temperature: Optional[float] = None,
         **kwargs,
     ):
         super().__init__(
-            model=model, api_key=api_key, base_url=base_url, language=language, **kwargs
+            model=model,
+            api_key=api_key,
+            base_url=base_url,
+            language=language,
+            prompt=prompt,
+            temperature=temperature,
+            **kwargs,
         )
 
     async def _transcribe(self, audio: bytes) -> Transcription:
         assert self._language is not None  # Assigned in the BaseWhisperSTTService class
-        return await self._client.audio.transcriptions.create(
-            file=("audio.wav", audio, "audio/wav"),
-            model=self.model_name,
-            response_format="json",
-            language=self._language,
-        )
+
+        # Build kwargs dict with only set parameters
+        kwargs = {
+            "file": ("audio.wav", audio, "audio/wav"),
+            "model": self.model_name,
+            "response_format": "json",
+            "language": self._language,
+        }
+
+        if self._prompt is not None:
+            kwargs["prompt"] = self._prompt
+
+        if self._temperature is not None:
+            kwargs["temperature"] = self._temperature
+
+        return await self._client.audio.transcriptions.create(**kwargs)

src/pipecat/services/openai.py

@@ -408,6 +408,8 @@ class OpenAISTTService(BaseWhisperSTTService):
         api_key: OpenAI API key. Defaults to None.
         base_url: API base URL. Defaults to None.
         language: Language of the audio input. Defaults to English.
+        prompt: Optional text to guide the model's style or continue a previous segment.
+        temperature: Optional sampling temperature between 0 and 1. Defaults to 0.0.
         **kwargs: Additional arguments passed to BaseWhisperSTTService.
     """
 
@@ -418,17 +420,37 @@ class OpenAISTTService(BaseWhisperSTTService):
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         language: Optional[Language] = Language.EN,
+        prompt: Optional[str] = None,
+        temperature: Optional[float] = None,
         **kwargs,
     ):
         super().__init__(
-            model=model, api_key=api_key, base_url=base_url, language=language, **kwargs
+            model=model,
+            api_key=api_key,
+            base_url=base_url,
+            language=language,
+            prompt=prompt,
+            temperature=temperature,
+            **kwargs,
         )
 
     async def _transcribe(self, audio: bytes) -> Transcription:
         assert self._language is not None  # Assigned in the BaseWhisperSTTService class
-        return await self._client.audio.transcriptions.create(
-            file=("audio.wav", audio, "audio/wav"), model=self.model_name, language=self._language
-        )
+
+        # Build kwargs dict with only set parameters
+        kwargs = {
+            "file": ("audio.wav", audio, "audio/wav"),
+            "model": self.model_name,
+            "language": self._language,
+        }
+
+        if self._prompt is not None:
+            kwargs["prompt"] = self._prompt
+
+        if self._temperature is not None:
+            kwargs["temperature"] = self._temperature
+
+        return await self._client.audio.transcriptions.create(**kwargs)
 
 
 class OpenAITTSService(TTSService):