Back to Models
GPT-4o Transcribe
openaiopenai/gpt-4o-transcribe
API guide
Audio transcription
Transcribe audio files with GPT-4o Transcribe through the OpenAI-compatible /v1/audio/transcriptions endpoint via TheRouter.
cURL
curl https://api.therouter.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-F "file=@recording.mp3" \
-F "model=openai/gpt-4o-transcribe" \
-F "response_format=json"Transcription with timestamps
Get segment-level timestamps in verbose JSON format for alignment and captioning workflows.
cURL
curl https://api.therouter.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-F "file=@recording.mp3" \
-F "model=openai/gpt-4o-transcribe" \
-F "response_format=verbose_json" \
-F "timestamp_granularities[]=segment"Language hinting
Improve accuracy and speed on known-language audio by passing the language parameter.
cURL
curl https://api.therouter.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-F "file=@conversation.mp3" \
-F "model=openai/gpt-4o-transcribe" \
-F "language=zh" \
-F "response_format=json"Context prompting
Use the prompt parameter to bias transcription towards domain-specific vocabulary.
cURL
curl https://api.therouter.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-F "file=@tech-meeting.mp3" \
-F "model=openai/gpt-4o-transcribe" \
-F "prompt=Transcription of an engineering meeting discussing Kubernetes deployment, Redis caching, and PostgreSQL sharding."Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date | openai.com β | 2026-05-28 | verified |
| Architecture | openai.com β | 2026-08-25 | verified |
| Endpoint | developers.openai.com β | 2026-05-28 | verified |
| Languages | openai.com β | 2026-08-25 | unknown |
| Training methodology | openai.com β | 2026-05-28 | verified |
| Max file size | tokenmix.ai β | 2026-05-28 | verified |
| Supported audio formats | developers.openai.com β | 2026-08-25 | verified |
| License | techcrunch.com β | 2026-05-28 | verified |
| FLEURS (multilingual WER β all languages) | openai.com β | 2026-08-25 | verified |
| Artificial Analysis AA-WER (combined rank) | openai.com β | 2026-08-25 | unknown |
| Common Voice & FLEURS (Dec 2025 snapshot) | developers.openai.com β | 2026-08-25 | verified |
| OpenAI ships December 2025 snapshot with further WER improvements | developers.openai.com β | 2026-05-28 | verified |
| OpenAI launches gpt-4o-transcribe and gpt-4o-mini-transcribe | openai.com β | 2026-05-28 | verified |
| How does gpt-4o-transcribe differ from whisper-1? | openai.com β | 2026-05-28 | to verify |
| Does gpt-4o-transcribe support speaker diarization? | tokenmix.ai β | 2026-05-28 | to verify |
| Can I get word-level timestamps? | tokenmix.ai β | 2026-05-28 | to verify |
| What's the maximum audio file size? | developers.openai.com β | 2026-05-28 | to verify |
| Which languages does gpt-4o-transcribe handle best? | techcrunch.com β | 2026-05-28 | to verify |
| Is gpt-4o-transcribe available through TheRouter? | api.therouter.ai β | 2026-05-28 | to verify |