> ## Documentation Index > Fetch the complete documentation index at: https://docs.zeroruntime.ai/llms.txt > Use this file to discover all available pages before exploring further. # Azure > JavaScript API reference for the azure speech-to-text plugin. ## AzureSTT Azure (Cognitive Services) speech-to-text provider. Creates a configured Azure Speech STT provider for use in a voice agent. ### Constructor ```typescript theme={null} new AzureSTT(opts: AzureSTTOptions) ``` Azure Speech key. Falls back to the `AZURE_SPEECH_KEY` env var. Azure Speech region. Falls back to the `AZURE_REGION` env var, then `'eastus'`. Recognition language code. Default: `'en-US'`. Input audio sample rate in Hz. Default: `16000`. Enable a phrase list to bias recognition. Phrases to bias recognition toward. ### close ```typescript theme={null} close(): Promise ``` Release any resources held by the provider. ### closeEmitter ```typescript theme={null} closeEmitter(): Promise ``` Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning. ### emit ```typescript theme={null} emit(event: string, ...args: any[]): void ``` ### getRuntimeConfig ```typescript theme={null} getRuntimeConfig(): Record ``` ### listenerCount ```typescript theme={null} listenerCount(event: string): number ``` ### off ```typescript theme={null} off(event: string, handler: EventHandler): void ``` ### on ```typescript theme={null} on(event: string, handler: EventHandler): EventHandler ``` ### once ```typescript theme={null} once(event: string, handler: EventHandler): EventHandler ``` ### onSttTranscript ```typescript theme={null} onSttTranscript(callback: SttTranscriptCallback): void ``` Register a callback to receive transcripts as they are produced. ### processAudio ```typescript theme={null} processAudio(_audioFrames: Uint8Array, _language?: string | null, ..._extra: any[]): Promise ``` Process a buffer of audio frames. Override in a custom provider. ### removeAllListeners ```typescript theme={null} removeAllListeners(event?: string): void ``` ### streamTranscribe ```typescript theme={null} streamTranscribe(_audioStream: AsyncIterable, ..._extra: any[]): AsyncIterator ``` Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider. *** ## AzureOpenAISTT Azure OpenAI speech-to-text provider. Creates a configured Azure OpenAI transcription provider for use in a voice agent. ### Constructor ```typescript theme={null} new AzureOpenAISTT(opts: AzureOpenAISTTOptions) ``` Azure OpenAI API key. Falls back to the `AZURE_API_KEY` then `AZURE_OPENAI_API_KEY` env vars, then `null`. Azure OpenAI resource endpoint. Falls back to the `AZURE_OPENAI_ENDPOINT` env var, then `null`. Azure deployment name. Falls back to the `AZURE_OPENAI_STT_DEPLOYMENT` env var, then `null`. Azure OpenAI REST API version. Default: `'2025-03-01-preview'`. Transcription model name. Default: `''`. Transcription language code. Default: `'en'`. Whether to use streaming transcription. Default: `false`. Input audio sample rate in Hz. Default: `48000`. Output audio sample rate in Hz. Default: `24000`. Optional prompt to bias transcription. Default: `null`. Sampling temperature. Default: `null`. Response format, e.g. `'json'`, `'text'`. Default: `'json'`. Turn-detection mode, e.g. `'server_vad'`. Default: `'server_vad'`. ### close ```typescript theme={null} close(): Promise ``` Release any resources held by the provider. ### closeEmitter ```typescript theme={null} closeEmitter(): Promise ``` Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning. ### emit ```typescript theme={null} emit(event: string, ...args: any[]): void ``` ### getRuntimeConfig ```typescript theme={null} getRuntimeConfig(): Record ``` ### listenerCount ```typescript theme={null} listenerCount(event: string): number ``` ### off ```typescript theme={null} off(event: string, handler: EventHandler): void ``` ### on ```typescript theme={null} on(event: string, handler: EventHandler): EventHandler ``` ### once ```typescript theme={null} once(event: string, handler: EventHandler): EventHandler ``` ### onSttTranscript ```typescript theme={null} onSttTranscript(callback: SttTranscriptCallback): void ``` Register a callback to receive transcripts as they are produced. ### processAudio ```typescript theme={null} processAudio(_audioFrames: Uint8Array, _language?: string | null, ..._extra: any[]): Promise ``` Process a buffer of audio frames. Override in a custom provider. ### removeAllListeners ```typescript theme={null} removeAllListeners(event?: string): void ``` ### streamTranscribe ```typescript theme={null} streamTranscribe(_audioStream: AsyncIterable, ..._extra: any[]): AsyncIterator ``` Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider. *** ## AzureOpenAISTTModel Supported Azure OpenAI STT transcription model names. ```typescript theme={null} type AzureOpenAISTTModel = 'gpt-4o-transcribe' | 'gpt-4o-mini-transcribe' | 'gpt-4o-transcribe-diarize' | 'whisper' ```