Audio modelActive
GPT-Transcribe
OpenAI
- Released
- -
- Data date
- September 24, 2026
- Model class
- Access
GPT-Transcribe is OpenAI’s file-oriented speech-to-text specialist. It handles completed audio files, streamed file transcripts, and committed turns in Realtime sessions. Unstructured context, keyword hints, and multiple language hints help with domain terms, multilingual audio, and code-switching. For completed recordings, the model is separate from GPT-Live-Transcribe, which handles ongoing speech.
GPT-Transcribe returns only text from completed audio. OpenAI lists function calling, structured outputs, and fine-tuning as unsupported. Speaker attribution and post-transcript formatting therefore sit outside the model rather than inside its transcription contract.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Speech recognitionSource |
| Access | APISource |
| API model ID | gpt-transcribeSource |
| Input | Audio fileSource |
| Output | TextSource |
| Task | TranscriptionSource |
| Supported details | File transcriptionSource |
| Capabilities | Unstructured context, keyword hints, language hints, and code-switchingSource |
Popularity
32.1 / 100
Published prices
- Transcription price
- $0.0045 per audio minuteSource
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | OpenAI model documentation (retrieved September 24, 2026) · OpenAI GPT-Transcribe model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |