Class STT<TModel>

Livekit Cloud Inference STT

Type Parameters

TModel extends STTModels

Hierarchy (view full)

stt.STT
- STT

Index

Constructors

constructor

new STT<TModel>(opts?): inference.STT<TModel>
Type Parameters
- TModel extends STTModels
Parameters
- Optional opts: {
      apiKey?: string;
      apiSecret?: string;
      baseURL?: string;
      encoding?: "pcm_s16le";
      language?: STTLanguages;
      model?: TModel;
      modelOptions?: inference.STTOptions<TModel>;
      sampleRate?: number;
  }
  - Optional apiKey?: string
  - Optional apiSecret?: string
  - Optional baseURL?: string
  - Optional encoding?: "pcm_s16le"
  - Optional language?: STTLanguages
  - Optional model?: TModel
  - Optional modelOptions?: inference.STTOptions<TModel>
  - Optional sampleRate?: number
Returns inference.STT<TModel>
Overrides STT.constructor
- Defined in inference/stt.ts:115

Accessors

capabilities

get capabilities(): STTCapabilities
Returns this STT's capabilities

Returns STTCapabilities
Inherited from BaseSTT.capabilities
- Defined in stt/stt.ts:111

label

get label(): string
Returns string
Overrides BaseSTT.label
- Defined in inference/stt.ts:162

Methods

close

close(): Promise<void>
Returns Promise<void>
Inherited from STT.close
- Defined in stt/stt.ts:145

connectWs

connectWs(timeout): Promise<WebSocket>
Parameters
- timeout: number
Returns Promise<WebSocket>
- Defined in inference/stt.ts:202

recognize

recognize(frame, abortSignal?): Promise<SpeechEvent>
Receives an audio buffer and returns transcription in the form of a SpeechEvent
Parameters
- frame: AudioBuffer
- Optional abortSignal: AbortSignal
Returns Promise<SpeechEvent>
Inherited from STT.recognize
- Defined in stt/stt.ts:116

stream

stream(options?): inference.stt.SpeechStream<TModel>
Returns a SpeechStream that can be used to push audio frames and receive transcriptions
Parameters
- Optional options: {
  connOptions?: APIConnectOptions;
  language?: string | AnyString;
  }
  Optional configuration including connection options
  - Optional connOptions?: APIConnectOptions
  - Optional language?: string | AnyString
Returns inference.stt.SpeechStream<TModel>
Overrides STT.stream
- Defined in inference/stt.ts:186

updateOptions

updateOptions(opts): void
Parameters
- opts: Partial<Pick<InferenceSTTOptions<TModel>, "language" | "model">>
Returns void
- Defined in inference/stt.ts:178

`Static` fromModelString

fromModelString(modelString): inference.STT<AnyString>
Parameters
- modelString: string
Returns inference.STT<AnyString>
- Defined in inference/stt.ts:166

Class STT<TModel>

Type Parameters

Hierarchy (view full)

Index

Constructors

Accessors

Methods

Constructors

constructor

Type Parameters

Parameters

Optional apiKey?: string

Optional apiSecret?: string

Optional baseURL?: string

Optional encoding?: "pcm_s16le"

Optional language?: STTLanguages

Optional model?: TModel

Optional modelOptions?: inference.STTOptions<TModel>

Optional sampleRate?: number

Returns inference.STT<TModel>

Accessors

capabilities

Returns STTCapabilities

label

Returns string

Methods

close

Returns Promise<void>

connectWs

Parameters

Returns Promise<WebSocket>

recognize

Parameters

Returns Promise<SpeechEvent>

stream

Parameters

Optional connOptions?: APIConnectOptions

Optional language?: string | AnyString

Returns inference.stt.SpeechStream<TModel>

updateOptions

Parameters

Returns void

Static fromModelString

Parameters

Returns inference.STT<AnyString>

Settings

Member Visibility

Theme

On This Page

`Optional` apiKey?: string

`Optional` apiSecret?: string

`Optional` baseURL?: string

`Optional` encoding?: "pcm_s16le"

`Optional` language?: STTLanguages

`Optional` model?: TModel

`Optional` modelOptions?: inference.STTOptions<TModel>

`Optional` sampleRate?: number

`Optional` connOptions?: APIConnectOptions

`Optional` language?: string | AnyString

`Static` fromModelString