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

refactor: Improve code reability and replace deprecated interruption frames

Browse Source
This commit is contained in:
shreyas-sarvam
2025-10-13 08:54:29 +05:30
parent 7c1e2793c5
commit 9babfe9fd9
1 changed files with 62 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

126
src/pipecat/services/sarvam/tts.py
View File

@@ -20,9 +20,9 @@ from pipecat.frames.frames import (
EndFrame, EndFrame,
ErrorFrame, ErrorFrame,
Frame, Frame,
InterruptionFrame,
LLMFullResponseEndFrame, LLMFullResponseEndFrame,
StartFrame, StartFrame,
StartInterruptionFrame,
TTSAudioRawFrame, TTSAudioRawFrame,
TTSStartedFrame, TTSStartedFrame,
TTSStoppedFrame, TTSStoppedFrame,
@@ -121,6 +121,9 @@ class SarvamHttpTTSService(TTSService):
default=0.6, default=0.6,
ge=0.01, ge=0.01,
le=1.0, le=1.0,
description="Controls the randomness of the output for bulbul v3 beta. "
"Lower values make the output more focused and deterministic, while "
"higher values make it more random. Range: 0.01 to 1.0. Default: 0.6.",
) )
def __init__( def __init__(
@@ -155,31 +158,31 @@ class SarvamHttpTTSService(TTSService):
self._base_url = base_url self._base_url = base_url
self._session = aiohttp_session self._session = aiohttp_session
if model == "bulbul:v3-beta" or model == "bulbul:v3": # Build base settings common to all models
# For bulbul v3 beta, exclude pace and loudness parameters self._settings = {
self._settings = { "language": (
"language": ( self.language_to_service_language(params.language) if params.language else "en-IN"
self.language_to_service_language(params.language) ),
if params.language "enable_preprocessing": params.enable_preprocessing,
else "en-IN" }
),
"enable_preprocessing": params.enable_preprocessing, # Add model-specific parameters
"temperature": getattr(params, "temperature", 0.6), if model in ("bulbul:v3-beta", "bulbul:v3"):
"model": model, # Include model in settings for v3 beta self._settings.update(
} {
"temperature": getattr(params, "temperature", 0.6),
"model": model,
}
)
else: else:
# For bulbul v2, include all parameters including pace and loudness self._settings.update(
self._settings = { {
"language": ( "pitch": params.pitch,
self.language_to_service_language(params.language) "pace": params.pace,
if params.language "loudness": params.loudness,
else "en-IN" "model": model,
), }
"pitch": params.pitch, )
"pace": params.pace,
"loudness": params.loudness,
"enable_preprocessing": params.enable_preprocessing,
}
self.set_model_name(model) self.set_model_name(model)
self.set_voice(voice_id) self.set_voice(voice_id)
@@ -310,7 +313,7 @@ class SarvamTTSService(InterruptibleTTSService):
) )
# For bulbul v3 beta with any speaker and temperature: # For bulbul v3 beta with any speaker and temperature:
# Note: pace and loudness are not supported for bulbul v3 beta # Note: pace and loudness are not supported for bulbul v3 and bulbul v3 beta
tts_v3 = SarvamTTSService( tts_v3 = SarvamTTSService(
api_key="your-api-key", api_key="your-api-key",
voice_id="speaker_name", voice_id="speaker_name",
@@ -386,8 +389,10 @@ class SarvamTTSService(InterruptibleTTSService):
voice_id: Voice identifier for synthesis (default "anushka"). voice_id: Voice identifier for synthesis (default "anushka").
url: WebSocket URL for connecting to the TTS backend (default production URL). url: WebSocket URL for connecting to the TTS backend (default production URL).
aiohttp_session: Optional shared aiohttp session. To maintain backward compatibility. aiohttp_session: Optional shared aiohttp session. To maintain backward compatibility.
.. deprecated:: 0.0.81 .. deprecated:: 0.0.81
aiohttp_session is no longer used. This parameter will be removed in a future version. aiohttp_session is no longer used. This parameter will be removed in a future version.
aggregate_sentences: Whether to merge multiple sentences into one audio chunk (default True). aggregate_sentences: Whether to merge multiple sentences into one audio chunk (default True).
sample_rate: Desired sample rate for the output audio in Hz (overrides default if set). sample_rate: Desired sample rate for the output audio in Hz (overrides default if set).
params: Optional input parameters to override global configuration. params: Optional input parameters to override global configuration.
@@ -423,44 +428,37 @@ class SarvamTTSService(InterruptibleTTSService):
self._api_key = api_key self._api_key = api_key
self.set_model_name(model) self.set_model_name(model)
self.set_voice(voice_id) self.set_voice(voice_id)
# Configuration parameters # Build base settings common to all models
if model == "bulbul:v3-beta" or model == "bulbul:v3": self._settings = {
# For bulbul v3 beta, exclude pace and loudness parameters "target_language_code": (
self._settings = { self.language_to_service_language(params.language) if params.language else "en-IN"
"target_language_code": ( ),
self.language_to_service_language(params.language) "speaker": voice_id,
if params.language "speech_sample_rate": 0,
else "en-IN" "enable_preprocessing": params.enable_preprocessing,
), "min_buffer_size": params.min_buffer_size,
"speaker": voice_id, "max_chunk_length": params.max_chunk_length,
"speech_sample_rate": 0, "output_audio_codec": params.output_audio_codec,
"enable_preprocessing": params.enable_preprocessing, "output_audio_bitrate": params.output_audio_bitrate,
"min_buffer_size": params.min_buffer_size, }
"max_chunk_length": params.max_chunk_length,
"output_audio_codec": params.output_audio_codec, # Add model-specific parameters
"output_audio_bitrate": params.output_audio_bitrate, if model in ("bulbul:v3-beta", "bulbul:v3"):
"temperature": getattr(params, "temperature", 0.6), self._settings.update(
"model": model, # Include model in settings for v3 beta {
} "temperature": getattr(params, "temperature", 0.6),
"model": model,
}
)
else: else:
# For bulbul v2, include all parameters including pace and loudness self._settings.update(
self._settings = { {
"target_language_code": ( "pitch": params.pitch,
self.language_to_service_language(params.language) "pace": params.pace,
if params.language "loudness": params.loudness,
else "en-IN" "model": model,
), }
"pitch": params.pitch, )
"pace": params.pace,
"speaker": voice_id,
"loudness": params.loudness,
"speech_sample_rate": 0,
"enable_preprocessing": params.enable_preprocessing,
"min_buffer_size": params.min_buffer_size,
"max_chunk_length": params.max_chunk_length,
"output_audio_codec": params.output_audio_codec,
"output_audio_bitrate": params.output_audio_bitrate,
}
self._started = False self._started = False
self._receive_task = None self._receive_task = None
@@ -529,7 +527,7 @@ class SarvamTTSService(InterruptibleTTSService):
direction: The direction to push the frame. direction: The direction to push the frame.
""" """
await super().push_frame(frame, direction) await super().push_frame(frame, direction)
if isinstance(frame, (TTSStoppedFrame, StartInterruptionFrame)): if isinstance(frame, (TTSStoppedFrame, InterruptionFrame)):
self._started = False self._started = False
async def process_frame(self, frame: Frame, direction: FrameDirection): async def process_frame(self, frame: Frame, direction: FrameDirection):