Audio modelDeprecated
GPT-4o Mini Transcribe
OpenAI
- Released
- -
- Data date
- September 24, 2026
- Model class
- Access
GPT-4o Mini Transcribe is a compact speech-to-text model built on GPT-4o Mini. OpenAI documents improvements in word error rate, language recognition, and accuracy compared with the original Whisper models. It accepts audio and returns text. With a 16,000-token context and a 2,000-token maximum output, its role stays focused on transcription.
However, OpenAI has announced its removal from the API on February 26, 2027, and names GPT-Transcribe and GPT-Live-Transcribe as replacements.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Speech recognitionSource |
| Access | APISource |
| API model ID | gpt-4o-mini-transcribeSource |
| Input | AudioSource |
| Output | TextSource |
| Task | TranscriptionSource |
| Supported details | Compact GPT-4o transcription modelSource |
| Context window | 16,000 tokensSource |
| Maximum output | 2,000 tokensSource |
| Knowledge cutoff | 2024-06-01Source |
| Capabilities | Improved word error rate and language recognition compared with the original Whisper modelsSource |
| Shutdown | Scheduled for February 26, 2027; OpenAI recommends GPT-Transcribe or GPT-Live-TranscribeSource |
Popularity
33.2 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | OpenAI model documentation (retrieved September 24, 2026) · OpenAI GPT-4o Mini Transcribe model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | Model lifecycle (retrieved September 24, 2026) · OpenAI model deprecations · 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 |