GPT-Realtime-Translate
GPT-Realtime-Translate converts incoming speech into translated speech and text while the source audio is still arriving. It uses a dedicated translation endpoint.
Translation is billed by audio duration
The listed charge is $0.034 per minute. The model emits translated audio and incremental transcript updates. Its documented context is 16,000 tokens with up to 2,000 output tokens; it is not a general chat endpoint.GPT-Realtime-Translate official model documentation
Review meaning across partial segments
Practical guidance. For a live presentation, review whether names, numbers and technical terms remain consistent across successive segments. Keep partial text distinct from completed text in the interface. A fluent translated sentence can still omit an important qualification.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gpt-realtime-translate |
| Context window | 16,000 tokens Published model context; input and output share this budget GPT-Realtime-Translate official model documentation |
| Maximum output | 2,000 tokens Published maximum output; bounded by the remaining context GPT-Realtime-Translate official model documentation |
| Input and output | audio in; audio, text outGPT-Realtime-Translate official model documentation |
| API routes | Realtime translation (v1/realtime/translations)GPT-Realtime-Translate official model documentation |
Related models
- GPT-Realtime-2.1
OpenAI · GPT Realtime
GPT-Realtime-2.1 combines conversational audio with reasoning and tool use.
Launch date not confirmedAPI - GPT-Realtime-1.5
OpenAI · GPT Realtime
GPT-Realtime-1.5 supports interactive voice agents with text, audio and image input.
Launch date not confirmedAPI - GPT-Realtime-2
OpenAI · GPT Realtime
GPT-Realtime-2 is a speech-to-speech model with configurable reasoning and tools.
Launch date not confirmedAPI - GPT-Realtime-2.1 Mini
OpenAI · GPT Realtime
GPT-Realtime-2.1 Mini is a distilled voice-reasoning model for lower-cost interactive audio.
Launch date not confirmedAPI