jason.woltjeandClaude Opus 4.6
af9c5799af
Critical fixes: - Fix FormData field name mismatch (audio -> file) to match backend FileInterceptor - Add /speech namespace to WebSocket connection URL - Pass auth token in WebSocket handshake options - Wrap audio.play() in try-catch for NotAllowedError and DOMException handling - Replace bare catch block with named error parameter and descriptive message - Add connect_error and disconnect event handlers to WebSocket - Update JSDoc to accurately describe batch transcription (not real-time partial) Important fixes: - Emit transcription-error before disconnect in gateway auth failures - Capture MediaRecorder error details and clean up media tracks on error - Change TtsDefaultConfig.format type from string to AudioFormat - Define canonical SPEECH_TIERS and AUDIO_FORMATS arrays as single source of truth - Fix voice count from 54 to 53 in provider, AGENTS.md, and docs - Fix inaccurate comments (Piper formats, tier prop, SpeachesProvider, TextValidationPipe) Co-Authored-By: Claude Opus 4.6 <[email protected]>
53 lines
1.4 KiB
TypeScript
53 lines
1.4 KiB
TypeScript
/**
|
|
* STT Provider Interface
|
|
*
|
|
* Defines the contract for speech-to-text provider implementations.
|
|
* All STT providers (e.g., Speaches/faster-whisper) must implement this interface.
|
|
*
|
|
* Issue #389
|
|
*/
|
|
|
|
import type { TranscribeOptions, TranscriptionResult } from "./speech-types";
|
|
|
|
/**
|
|
* Interface for speech-to-text providers.
|
|
*
|
|
* Implementations wrap an OpenAI-compatible API endpoint for transcription.
|
|
*
|
|
* @example
|
|
* ```typescript
|
|
* class SpeachesSttProvider implements ISTTProvider {
|
|
* readonly name = "speaches";
|
|
*
|
|
* async transcribe(audio: Buffer, options?: TranscribeOptions): Promise<TranscriptionResult> {
|
|
* // Call speaches API via OpenAI SDK
|
|
* }
|
|
*
|
|
* async isHealthy(): Promise<boolean> {
|
|
* // Check endpoint health
|
|
* }
|
|
* }
|
|
* ```
|
|
*/
|
|
export interface ISTTProvider {
|
|
/** Provider name for logging and identification */
|
|
readonly name: string;
|
|
|
|
/**
|
|
* Transcribe audio data to text.
|
|
*
|
|
* @param audio - Raw audio data as a Buffer
|
|
* @param options - Optional transcription parameters
|
|
* @returns Transcription result with text and metadata
|
|
* @throws {Error} If transcription fails
|
|
*/
|
|
transcribe(audio: Buffer, options?: TranscribeOptions): Promise<TranscriptionResult>;
|
|
|
|
/**
|
|
* Check if the provider is healthy and available.
|
|
*
|
|
* @returns true if the provider endpoint is reachable and ready
|
|
*/
|
|
isHealthy(): Promise<boolean>;
|
|
}
|