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

Merge pull request #3991 from pipecat-ai/pk/fix-out-of-date-docstrings

Browse Source 
Fix out of date docstrings
This commit is contained in:
kompfner
2026-03-11 10:54:40 -04:00
committed by GitHub
parent 7e88b13421 3cbd27d202
commit cbb4835e7b
7 changed files with 59 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3991.changed.md Normal file
View File

@@ -0,0 +1 @@
- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of `OpenAIRealtimeSTTSettings`, making it runtime-updatable via `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is deprecated as of 0.0.106.

13
src/pipecat/services/camb/tts.py
View File

@@ -158,13 +158,20 @@ class CambTTSService(TTSService):
Example::
# Basic usage with mars-flash (fast)
tts = CambTTSService(api_key="your-api-key", model="mars-flash")
tts = CambTTSService(
api_key="your-api-key",
settings=CambTTSService.Settings(
model="mars-flash"
)
)
# High quality with mars-pro
tts = CambTTSService(
api_key="your-api-key",
voice_id=12345,
model="mars-pro",
settings=CambTTSService.Settings(
voice=12345,
model="mars-pro",
)
)
"""

2
src/pipecat/services/deepgram/sagemaker/stt.py
View File

@@ -69,7 +69,7 @@ class DeepgramSageMakerSTTService(STTService):
stt = DeepgramSageMakerSTTService(
endpoint_name="my-deepgram-endpoint",
region="us-east-2",
settings=DeepgramSageMakerSTTSettings(
settings=DeepgramSageMakerSTTService.Settings(
model="nova-3",
language="en",
interim_results=True,

4
src/pipecat/services/deepgram/sagemaker/tts.py
View File

@@ -63,7 +63,9 @@ class DeepgramSageMakerTTSService(TTSService):
tts = DeepgramSageMakerTTSService(
endpoint_name="my-deepgram-tts-endpoint",
region="us-east-2",
voice="aura-2-helena-en",
settings=DeepgramSageMakerTTSService.Settings(
voice="aura-2-helena-en",
)
)
"""

10
src/pipecat/services/google/tts.py
View File

@@ -1014,8 +1014,8 @@ class GoogleTTSService(GoogleBaseTTSService):
tts = GoogleTTSService(
credentials_path="/path/to/service-account.json",
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleTTSService.InputParams(
settings=GoogleTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
)
)
@@ -1191,9 +1191,9 @@ class GeminiTTSService(GoogleBaseTTSService):
tts = GeminiTTSService(
credentials_path="/path/to/service-account.json",
model="gemini-2.5-flash-tts",
voice_id="Kore",
params=GeminiTTSService.InputParams(
settings=GeminiTTSService.Settings(
model="gemini-2.5-flash-tts",
voice="Kore",
language=Language.EN_US,
prompt="Say this in a friendly and helpful tone"
)

24
src/pipecat/services/openai/stt.py
View File

@@ -187,9 +187,15 @@ class OpenAIRealtimeSTTSettings(STTSettings):
Parameters:
prompt: Optional prompt text to guide transcription style.
noise_reduction: Noise reduction mode. ``"near_field"`` for close
microphones, ``"far_field"`` for distant microphones, or ``None``
to disable.
"""
prompt: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
noise_reduction: Literal["near_field", "far_field"] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
class OpenAIRealtimeSTTService(WebsocketSTTService):
@@ -220,8 +226,10 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
stt = OpenAIRealtimeSTTService(
api_key="sk-...",
model="gpt-4o-transcribe",
noise_reduction="near_field",
settings=OpenAIRealtimeSTTService.Settings(
model="gpt-4o-transcribe",
noise_reduction="near_field",
),
)
"""
@@ -274,6 +282,9 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
noise_reduction: Noise reduction mode. ``"near_field"`` for
close microphones, ``"far_field"`` for distant
microphones, or ``None`` to disable.
.. deprecated:: 0.0.106
Use ``settings=OpenAIRealtimeSTTSettings(noise_reduction=...)`` instead.
should_interrupt: Whether to interrupt bot output when
speech is detected by server-side VAD. Only applies when
turn detection is enabled. Defaults to True.
@@ -295,6 +306,7 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
model="gpt-4o-transcribe",
language=Language.EN,
prompt=None,
noise_reduction=None,
)
# --- 2. Deprecated direct-arg overrides ---
@@ -307,6 +319,9 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
if prompt is not None:
_warn_deprecated_param("prompt", OpenAIRealtimeSTTSettings, "prompt")
default_settings.prompt = prompt
if noise_reduction is not None:
_warn_deprecated_param("noise_reduction", OpenAIRealtimeSTTSettings, "noise_reduction")
default_settings.noise_reduction = noise_reduction
# --- 3. (no params object for this service) ---
@@ -324,7 +339,6 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
self._base_url = base_url
self._turn_detection = turn_detection
self._noise_reduction = noise_reduction
self._should_interrupt = should_interrupt
self._receive_task = None
@@ -544,9 +558,9 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
input_audio["turn_detection"] = self._turn_detection
# Noise reduction
if self._noise_reduction:
if self._settings.noise_reduction:
input_audio["noise_reduction"] = {
"type": self._noise_reduction,
"type": self._settings.noise_reduction,
}
await self._ws_send(

40
src/pipecat/services/sarvam/tts.py
View File

@@ -326,28 +326,28 @@ class SarvamHttpTTSService(TTSService):
# Using bulbul:v2 (default)
tts = SarvamHttpTTSService(
api_key="your-api-key",
voice_id="anushka",
model="bulbul:v2",
aiohttp_session=session,
params=SarvamHttpTTSService.InputParams(
settings=SarvamHttpTTSService.Settings(
voice="anushka",
model="bulbul:v2",
language=Language.HI,
pitch=0.1,
pace=1.2,
loudness=1.5
)
loudness=1.5,
),
)
# Using bulbul:v3-beta with temperature control
tts_v3 = SarvamHttpTTSService(
api_key="your-api-key",
voice_id="aditya", # Use v3 speaker
model="bulbul:v3-beta",
aiohttp_session=session,
params=SarvamHttpTTSService.InputParams(
settings=SarvamHttpTTSService.Settings(
voice="aditya", # Use v3 speaker
model="bulbul:v3-beta",
language=Language.HI,
pace=1.2, # Range: 0.5-2.0 for v3
temperature=0.8
)
temperature=0.8,
),
)
"""
@@ -693,26 +693,26 @@ class SarvamTTSService(InterruptibleTTSService):
# Using bulbul:v2 (default)
tts = SarvamTTSService(
api_key="your-api-key",
voice_id="anushka",
model="bulbul:v2",
params=SarvamTTSService.InputParams(
settings=SarvamTTSService.Settings(
voice="anushka",
model="bulbul:v2",
language=Language.HI,
pitch=0.1,
pace=1.2,
loudness=1.5
)
loudness=1.5,
),
)
# Using bulbul:v3-beta with temperature control
tts_v3 = SarvamTTSService(
api_key="your-api-key",
voice_id="aditya", # Use v3 speaker
model="bulbul:v3-beta",
params=SarvamTTSService.InputParams(
settings=SarvamTTSService.Settings(
voice="aditya", # Use v3 speaker
model="bulbul:v3-beta",
language=Language.HI,
pace=1.2, # Range: 0.5-2.0 for v3
temperature=0.8
)
temperature=0.8,
),
)
See https://docs.sarvam.ai/api-reference-docs/text-to-speech/stream for API details.