OpenAITTSService: add speed arg

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added a `speed` arg to `OpenAITTSService` to control the speed of the voice
+  response.
+
 - Added `FrameProcessor.push_interruption_task_frame_and_wait()`. Use this
   method to programatically interrupt the bot from any part of the
   pipeline. This guarantees that all the processors in the pipeline are

src/pipecat/services/openai/tts.py

@@ -64,6 +64,7 @@ class OpenAITTSService(TTSService):
         model: str = "gpt-4o-mini-tts",
         sample_rate: Optional[int] = None,
         instructions: Optional[str] = None,
+        speed: Optional[float] = None,
         **kwargs,
     ):
         """Initialize OpenAI TTS service.
@@ -75,6 +76,7 @@ class OpenAITTSService(TTSService):
             model: TTS model to use. Defaults to "gpt-4o-mini-tts".
             sample_rate: Output audio sample rate in Hz. If None, uses OpenAI's default 24kHz.
             instructions: Optional instructions to guide voice synthesis behavior.
+            speed: Voice speed control (0.25 to 4.0, default 1.0).
             **kwargs: Additional keyword arguments passed to TTSService.
         """
         if sample_rate and sample_rate != self.OPENAI_SAMPLE_RATE:
@@ -84,6 +86,7 @@ class OpenAITTSService(TTSService):
             )
         super().__init__(sample_rate=sample_rate, **kwargs)
 
+        self._speed = speed
         self.set_model_name(model)
         self.set_voice(voice)
         self._instructions = instructions
@@ -133,17 +136,22 @@ class OpenAITTSService(TTSService):
         try:
             await self.start_ttfb_metrics()
 
-            # Setup extra body parameters
+            # Setup API parameters
-            extra_body = {}
+            create_params = {
+                "input": text,
+                "model": self.model_name,
+                "voice": VALID_VOICES[self._voice_id],
+                "response_format": "pcm",
+            }
+
             if self._instructions:
-                extra_body["instructions"] = self._instructions
+                create_params["instructions"] = self._instructions
+
+            if self._speed:
+                create_params["speed"] = self._speed
 
             async with self._client.audio.speech.with_streaming_response.create(
-                input=text,
+                **create_params
-                model=self.model_name,
-                voice=VALID_VOICES[self._voice_id],
-                response_format="pcm",
-                extra_body=extra_body,
             ) as r:
                 if r.status_code != 200:
                     error = await r.text()

uv.lock

@@ -4307,6 +4307,12 @@ local-smart-turn = [
     { name = "torchaudio" },
     { name = "transformers" },
 ]
+local-smart-turn-v3 = [
+    { name = "onnxruntime" },
+    { name = "torch" },
+    { name = "torchaudio" },
+    { name = "transformers" },
+]
 mcp = [
     { name = "mcp", extra = ["cli"] },
 ]
@@ -4460,7 +4466,8 @@ requires-dist = [
     { name = "numba", specifier = "==0.61.2" },
     { name = "numpy", specifier = ">=1.26.4,<3" },
     { name = "nvidia-riva-client", marker = "extra == 'riva'", specifier = "~=2.21.1" },
-    { name = "onnxruntime", marker = "extra == 'silero'", specifier = "~=1.20.1" },
+    { name = "onnxruntime", marker = "extra == 'local-smart-turn-v3'", specifier = ">=1.20.1,<2" },
+    { name = "onnxruntime", marker = "extra == 'silero'", specifier = ">=1.20.1,<2" },
     { name = "openai", specifier = ">=1.74.0,<=1.99.1" },
     { name = "opencv-python", marker = "extra == 'webrtc'", specifier = "~=4.11.0.86" },
     { name = "openpipe", marker = "extra == 'openpipe'", specifier = "~=4.50.0" },
@@ -4488,8 +4495,11 @@ requires-dist = [
     { name = "tenacity", marker = "extra == 'livekit'", specifier = ">=8.2.3,<10.0.0" },
     { name = "timm", marker = "extra == 'moondream'", specifier = "~=1.0.13" },
     { name = "torch", marker = "extra == 'local-smart-turn'", specifier = ">=2.5.0,<3" },
+    { name = "torch", marker = "extra == 'local-smart-turn-v3'", specifier = ">=2.5.0,<3" },
     { name = "torchaudio", marker = "extra == 'local-smart-turn'", specifier = ">=2.5.0,<3" },
+    { name = "torchaudio", marker = "extra == 'local-smart-turn-v3'", specifier = ">=2.5.0,<3" },
     { name = "transformers", marker = "extra == 'local-smart-turn'" },
+    { name = "transformers", marker = "extra == 'local-smart-turn-v3'" },
     { name = "transformers", marker = "extra == 'moondream'", specifier = ">=4.48.0" },
     { name = "transformers", marker = "extra == 'ultravox'", specifier = ">=4.48.0" },
     { name = "uvicorn", marker = "extra == 'runner'", specifier = ">=0.32.0,<1.0.0" },
@@ -4513,7 +4523,7 @@ requires-dist = [
     { name = "websockets", marker = "extra == 'soniox'", specifier = ">=13.1,<15.0" },
     { name = "websockets", marker = "extra == 'websocket'", specifier = ">=13.1,<15.0" },
 ]
-provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "deepseek", "daily", "deepgram", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "inworld", "krisp", "koala", "langchain", "livekit", "lmnt", "local", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "nim", "neuphonic", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "rime", "riva", "runner", "sambanova", "sarvam", "sentry", "local-smart-turn", "remote-smart-turn", "silero", "simli", "soniox", "soundfile", "speechmatics", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "whisper"]
+provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "deepseek", "daily", "deepgram", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "inworld", "krisp", "koala", "langchain", "livekit", "lmnt", "local", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "nim", "neuphonic", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "rime", "riva", "runner", "sambanova", "sarvam", "sentry", "local-smart-turn", "local-smart-turn-v3", "remote-smart-turn", "silero", "simli", "soniox", "soundfile", "speechmatics", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "whisper"]
 
 [package.metadata.requires-dev]
 dev = [