AI Gateway · Component · speech-transcription-translation
Speech transcription and audio translation adapters
What it does
Dispatch audio transcription or supported translation with language/format controls. One gateway variant routes multipart; another only supports asr-1.0; other adapters differ by provider. Long-audio assembly is separate.
Core pattern
Audio transcription or translation + language and format controls
- Input
- Audio request in JSON/multipart form
- Output
- Transcript or translated transcript
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| audio | — | — | — |
| audio_url | — | — | — |
| language | — | — | — |
| target_languages | array | [] | — |
| max_audio_bytes | integer | 52428800 | 1–1073741824 |
Maturity and limits
Concrete audio/transcriptions and audio/translations handlers. Source paths were inspected statically; tests and live integrations were not executed. This rating describes implemented code, not production validation.
Credential-bearing configuration is excluded from this inventory. MIT; retain notices. Provider compatibility is configuration-dependent; metadata/privacy and optional payload plugins need review. Static inspection only. Variant-specific dependencies, limits and weaker maturity are recorded under variants; these implementations are alternatives, not one deployed system.
Used in pipelines
Industry tags
- HealthcareTransferable use
For organizing consented appointment-service interviews, use audio transcription or translation followed by language and format controls.
Skills pack
Contract scaffold and deterministic mock
Download · 13KBSHA-256 33cfdb0b93da7521b3248207f52923c89774a373992a34d9769c8e81aa803c03
Related components
-
Image generation, editing, upscaling and prediction jobs
Image generation or masked edits + async result tracking
Working 1 pipeline -
Asynchronous video generation and retained media
Async media requests + result polling and usage records
Working 1 pipeline -
Remote browser sessions and artifacts
Browser operations + screenshots and structured page extraction
Working 1 pipeline -
Provider text summarization, sentiment and intent analysis
Supplied text topic and intent extraction + structured summaries
Working 2 pipelines