VadAnalyzer
- class pipecat.audio.vad.vad_analyzer.VADState(*values)[source]
Bases:
Enum- QUIET = 1
- STARTING = 2
- SPEAKING = 3
- STOPPING = 4
- class pipecat.audio.vad.vad_analyzer.VADParams(*, confidence=0.7, start_secs=0.2, stop_secs=0.8, min_volume=0.6)[source]
Bases:
BaseModel- Parameters:
confidence (float)
start_secs (float)
stop_secs (float)
min_volume (float)
- confidence: float
- start_secs: float
- stop_secs: float
- min_volume: float
- model_config: ClassVar[ConfigDict] = {}
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
- class pipecat.audio.vad.vad_analyzer.VADAnalyzer(*, sample_rate=None, params=None)[source]
Bases:
ABC- Parameters:
sample_rate (int | None)
params (VADParams | None)
- property sample_rate: int
- property num_channels: int
- property params: VADParams
- abstractmethod num_frames_required()[source]
- Return type:
int
- abstractmethod voice_confidence(buffer)[source]
- Return type:
float
- set_sample_rate(sample_rate)[source]
- Parameters:
sample_rate (int)
- set_params(params)[source]
- Parameters:
params (VADParams)
- analyze_audio(buffer)[source]
- Return type:
VADState