OpenAI /audio/translations
OpenAI's translate-to-English audio endpoint.
OpenAI's translate-to-English audio endpoint.
Best for quick translation of non-English audio into English text. Pricing: from $0.006/min (whisper-1).
What it is
OpenAI's /audio/translations endpoint accepts non-English audio and returns English text. Uses the same underlying Whisper-class models as /audio/transcriptions. Useful for one-pass localization workflows or for English subtitling of multilingual source content. Best fit: quick translation of non-english audio into english text. Caveats: translation is english-output only; no native diarization. Pricing as listed: from $0.006/min (whisper-1). Feature flags from vendor docs: word-level timestamps. Directory tags: commercial-api, translation. Last vendor-page check: 2026-05-12. The product slots into the broader voice-AI tooling landscape and is best evaluated head-to-head with adjacent vendors in its subcategory; verify current language coverage, region availability, and compliance terms on the vendor's public docs at time of build.
Watch out for: Translation is English-output only; no native diarization.
Install / use
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 99 |
| HIPAA eligible | No |
OpenAI /audio/translations vs Whipscribe
| Feature | OpenAI /audio/translations | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | from $0.006/min (whisper-1) | free beta |
| Speaker diarization | No | Yes |
| Word timestamps | Yes | Yes |
| Streaming | No | No |
| Languages | 99 | 99 |
| Platforms | API | Web, API, MCP |
Alternatives to OpenAI /audio/translations
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.