Module speech_to_text 

Structs

CosineSimilarity

PeerInputAudioIndexed

A raw audio chunk bundled with its sequence sequence index.

SpeakerId

A unique identifier for a speaker.

SpeakerSegment

SpeechDetected

Signal indicating that speech activity has been detected.

SpeechTranscript

A transcribed segment of speech.

Word

Represents a single word within a transcription.

WordOverlap

Enums

InputVoiceAudio

Represents an audio chunk with its associated voice activity status.

InternalSpeaker

Traits

DiarizationPlugin

STTPlugin

TTSPlugin

Functions

calculate_chunk_indices

Calculates the discrete audio chunk indices for a given continuous time range.

Type Aliases

SpeakerHeuristicCallback