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
sourceURLretrieved
Release dateopenai.com β†—2026-05-28verified
Architectureopenai.com β†—2026-08-25verified
Endpointdevelopers.openai.com β†—2026-05-28verified
Languagesopenai.com β†—2026-08-25unknown
Training methodologyopenai.com β†—2026-05-28verified
Max file sizetokenmix.ai β†—2026-05-28verified
Supported audio formatsdevelopers.openai.com β†—2026-08-25verified
Licensetechcrunch.com β†—2026-05-28verified
FLEURS (multilingual WER β€” all languages)openai.com β†—2026-08-25verified
Artificial Analysis AA-WER (combined rank)openai.com β†—2026-08-25unknown
Common Voice & FLEURS (Dec 2025 snapshot)developers.openai.com β†—2026-08-25verified
OpenAI ships December 2025 snapshot with further WER improvementsdevelopers.openai.com β†—2026-05-28verified
OpenAI launches gpt-4o-transcribe and gpt-4o-mini-transcribeopenai.com β†—2026-05-28verified
How does gpt-4o-transcribe differ from whisper-1?openai.com β†—2026-05-28to verify
Does gpt-4o-transcribe support speaker diarization?tokenmix.ai β†—2026-05-28to verify
Can I get word-level timestamps?tokenmix.ai β†—2026-05-28to verify
What's the maximum audio file size?developers.openai.com β†—2026-05-28to verify
Which languages does gpt-4o-transcribe handle best?techcrunch.com β†—2026-05-28to verify
Is gpt-4o-transcribe available through TheRouter?api.therouter.ai β†—2026-05-28to verify
Help & contact