OpenAI /audio/transcriptions (whisper-1, gpt-4o-transcribe)
OpenAI's hosted Whisper + gpt-4o-transcribe models, batch endpoint.
OpenAI's hosted Whisper + gpt-4o-transcribe models, batch endpoint.
Best for teams who want the simplest possible hosted Whisper with OpenAI auth + billing. Pricing: from $0.006/min (whisper-1).
What it is
OpenAI's /audio/transcriptions endpoint covers the whisper-1 model and the newer gpt-4o-transcribe + gpt-4o-mini-transcribe transcription models. Batch only (Realtime API is a separate streaming endpoint). Pricing varies by model; whisper-1 has the simplest per-minute price. No native diarization; pair with a separate diarization pipeline if needed. Best fit: teams who want the simplest possible hosted whisper with openai auth + billing. Caveats: distinct from the 'openai-whisper-api' entry — this row is the canonical /audio/transcriptions rest endpoint covering whisper-1 + gpt-4o-transcribe variants. Pricing as listed: from $0.006/min (whisper-1). Feature flags from vendor docs: word-level timestamps. Directory tags: commercial-api. Last vendor-page check: 2026-05-12.
Watch out for: Distinct from the 'openai-whisper-api' entry — this row is the canonical /audio/transcriptions REST endpoint covering whisper-1 + gpt-4o-transcribe variants.
Install / use
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 99 |
| HIPAA eligible | No |
OpenAI /audio/transcriptions (whisper-1, gpt-4o-transcribe) vs Whipscribe
| Feature | OpenAI /audio/transcriptions (whisper-1, gpt-4o-transcribe) | 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/transcriptions (whisper-1, gpt-4o-transcribe)
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.