Models

class pipecat.services.assemblyai.models.Word(*, start, end, text, confidence, word_is_final)[source]

Bases: BaseModel

Represents a single word in a transcription with timing and confidence.

Parameters:

  • start (int)

  • end (int)

  • text (str)

  • confidence (float)

  • word_is_final (bool)

start: int
end: int
text: str
confidence: float
word_is_final: bool
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.assemblyai.models.BaseMessage(*, type)[source]

Bases: BaseModel

Base class for all AssemblyAI WebSocket messages.

Parameters:

type (str)

type: str
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.assemblyai.models.BeginMessage(*, type='Begin', id, expires_at)[source]

Bases: BaseMessage

Message sent when a new session begins.

Parameters:

  • type (Literal['Begin'])

  • id (str)

  • expires_at (int)

type: Literal['Begin']
id: str
expires_at: int
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.assemblyai.models.TurnMessage(*, type='Turn', turn_order, turn_is_formatted, end_of_turn, transcript, end_of_turn_confidence, words)[source]

Bases: BaseMessage

Message containing transcription data for a turn of speech.

Parameters:

  • type (Literal['Turn'])

  • turn_order (int)

  • turn_is_formatted (bool)

  • end_of_turn (bool)

  • transcript (str)

  • end_of_turn_confidence (float)

  • words (List[Word])

type: Literal['Turn']
turn_order: int
turn_is_formatted: bool
end_of_turn: bool
transcript: str
end_of_turn_confidence: float
words: List[Word]
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.assemblyai.models.TerminationMessage(*, type='Termination', audio_duration_seconds, session_duration_seconds)[source]

Bases: BaseMessage

Message sent when the session is terminated.

Parameters:

  • type (Literal['Termination'])

  • audio_duration_seconds (float)

  • session_duration_seconds (float)

type: Literal['Termination']
audio_duration_seconds: float
session_duration_seconds: float
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.assemblyai.models.AssemblyAIConnectionParams(*, sample_rate=16000, encoding='pcm_s16le', formatted_finals=True, word_finalization_max_wait_time=None, end_of_turn_confidence_threshold=None, min_end_of_turn_silence_when_confident=None, max_turn_silence=None)[source]

Bases: BaseModel

Parameters:

  • sample_rate (int)

  • encoding (Literal['pcm_s16le', 'pcm_mulaw'])

  • formatted_finals (bool)

  • word_finalization_max_wait_time (int | None)

  • end_of_turn_confidence_threshold (float | None)

  • min_end_of_turn_silence_when_confident (int | None)

  • max_turn_silence (int | None)

sample_rate: int
encoding: Literal['pcm_s16le', 'pcm_mulaw']
formatted_finals: bool
word_finalization_max_wait_time: int | None
end_of_turn_confidence_threshold: float | None
min_end_of_turn_silence_when_confident: int | None
max_turn_silence: int | None
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].