Audio modelActive
GPT-Realtime Translate
OpenAI
- Released
- -
- Data date
- September 22, 2026
- Model class
- Access
GPT-Realtime-Translate is a narrowly focused speech-to-speech translation model. It consumes incoming audio, streams translated audio, and returns transcript deltas while the source speech is still arriving. The model uses a dedicated Realtime translation endpoint. It is not meant for general reasoning or batch document translation.
GPT-Realtime-Translate uses a 16,000-token context and returns up to 2,000 tokens. OpenAI bills it by audio duration rather than text tokens. Gemini 3.5 Live Translate serves a similar speech-to-speech role and Google documents support for more than 70 languages; GPT-Realtime-Translate also returns transcript deltas.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Real-time translationSource |
| Access | APISource |
| API model ID | gpt-realtime-translateSource |
| Input | AudioSource |
| Output | Audio and transcriptSource |
| Task | Speech-to-speech translationSource |
| Supported details | Streaming audio translationSource |
| Context window | 16,000 tokensSource |
| Maximum output | 2,000 tokensSource |
| Knowledge cutoff | 2024-09-30Source |
Popularity
35.3 / 100
Published prices
- Translation price
- $0.034 per audio minuteSource
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | OpenAI model documentation (retrieved September 22, 2026) · OpenAI GPT-Realtime-Translate 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 |