wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tavus support for custom output rate

Browse Source
This commit is contained in:
Lucas Rothman
2025-03-11 16:02:33 -07:00
parent 5bd359ada9
commit ecc4411128
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/pipecat/services/tavus.py
View File

@@ -37,6 +37,7 @@ class TavusVideoService(AIService):
replica_id: str, replica_id: str,
persona_id: str = "pipecat0", # Use `pipecat0` so that your TTS voice is used in place of the Tavus persona persona_id: str = "pipecat0", # Use `pipecat0` so that your TTS voice is used in place of the Tavus persona
session: aiohttp.ClientSession, session: aiohttp.ClientSession,
output_sample_rate: int = 16000,
**kwargs, **kwargs,
) -> None: ) -> None:
super().__init__(**kwargs) super().__init__(**kwargs)
@@ -44,6 +45,7 @@ class TavusVideoService(AIService):
self._replica_id = replica_id self._replica_id = replica_id
self._persona_id = persona_id self._persona_id = persona_id
self._session = session self._session = session
self._output_sample_rate = output_sample_rate
self._conversation_id: str self._conversation_id: str
@@ -94,7 +96,7 @@ class TavusVideoService(AIService):
async def _encode_audio_and_send(self, audio: bytes, in_rate: int, done: bool) -> None: async def _encode_audio_and_send(self, audio: bytes, in_rate: int, done: bool) -> None:
"""Encodes audio to base64 and sends it to Tavus""" """Encodes audio to base64 and sends it to Tavus"""
if not done: if not done:
audio = await self._resampler.resample(audio, in_rate, 16000) audio = await self._resampler.resample(audio, in_rate, self._output_sample_rate)
audio_base64 = base64.b64encode(audio).decode("utf-8") audio_base64 = base64.b64encode(audio).decode("utf-8")
logger.trace(f"{self}: sending {len(audio)} bytes") logger.trace(f"{self}: sending {len(audio)} bytes")
await self._send_audio_message(audio_base64, done=done) await self._send_audio_message(audio_base64, done=done)
@@ -108,7 +110,7 @@ class TavusVideoService(AIService):
elif isinstance(frame, TTSAudioRawFrame): elif isinstance(frame, TTSAudioRawFrame):
await self._encode_audio_and_send(frame.audio, frame.sample_rate, done=False) await self._encode_audio_and_send(frame.audio, frame.sample_rate, done=False)
elif isinstance(frame, TTSStoppedFrame): elif isinstance(frame, TTSStoppedFrame):
await self._encode_audio_and_send(b"\x00", 16000, done=True) await self._encode_audio_and_send(b"\x00", self._output_sample_rate, done=True)
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()
await self.stop_processing_metrics() await self.stop_processing_metrics()
elif isinstance(frame, StartInterruptionFrame): elif isinstance(frame, StartInterruptionFrame):
@@ -137,6 +139,7 @@ class TavusVideoService(AIService):
"inference_id": self._current_idx_str, "inference_id": self._current_idx_str,
"audio": audio_base64, "audio": audio_base64,
"done": done, "done": done,
"sample_rate": self._output_sample_rate,
}, },
} }
) )