* @module voice-pipeline/providers/BatchSTTFallback Wraps multiple {@link IBatchSTT} providers in priority order. Tries each in sequence; returns the first successful transcription. Throws an aggregate error if every provider fails. A provider MAY signal "the clip contained no sp
// Source: https://github.com/framerslab/agentos | License: Apache-2.0
// Provided via justclaw.it.com; keep this notice with the code.
/**
* @module voice-pipeline/providers/BatchSTTFallback
*
* Wraps multiple {@link IBatchSTT} providers in priority order. Tries each in
* sequence; returns the first successful transcription. Throws an aggregate
* error if every provider fails.
*
* A provider MAY signal "the clip contained no speech" by throwing
* {@link EmptyTranscriptError}. That is a REAL result (silence), not a provider
* failure, so the fallback rethrows it immediately instead of burning the next
* provider on the same silent audio.
*/
import type { IBatchSTT, BatchSTTConfig, BatchSTTResult } from '../types.js';
/**
* Thrown by a batch STT provider when the audio yielded
... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key