{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/gpt-realtime-translate/","md":"https://postcutoff.com/m/gpt-realtime-translate/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"gpt-realtime-translate","name":"GPT-Realtime-Translate","org":"OpenAI","family":"GPT Realtime","released":"2026-05-07","status":"current","type":"audio/speech","modality_in":["audio"],"modality_out":["audio","text"],"open_weights":false,"model_license":"proprietary","context_window":16000,"max_output":2000,"knowledge_cutoff":null,"pricing":{"per_minute":0.034,"unit":"per minute of audio (USD), billed by duration not tokens","source":"https://developers.openai.com/api/docs/pricing"},"price_line":"$0.034 per minute","access":[{"provider":"OpenAI API","model_id":"gpt-realtime-translate","endpoint":"https://api.openai.com/v1/realtime/translations","docs":"https://developers.openai.com/api/docs/models/gpt-realtime-translate"}],"capabilities":[{"name":"Streaming speech-to-speech translation","detail":"Simultaneous interpretation from 70+ input languages into 13 output languages, emitting translated audio plus transcript deltas while the speaker is still talking.","first":false,"discovered":"launch","source":"https://www.ghacks.net/2026/05/11/openai-releases-three-new-realtime-voice-models-for-the-api-with-gpt-5-class-reasoning/"},{"name":"Dedicated translation endpoint","detail":"Served only on v1/realtime/translations (not the general Realtime or Chat endpoints).","first":false,"discovered":"launch","source":"https://developers.openai.com/api/docs/models/gpt-realtime-translate"}],"entry":"2026-05-07-openai-gpt-realtime-2-translate-whisper","notes":"Language counts (70+ in / 13 out) come from press coverage of the launch post; the docs page does not list languages. Latency not specified. Google's comparable model is gemini-3.5-live-translate-preview (June 2026).","verified":"2026-09-29","body_md":"Live interpretation for calls, events and apps.\n\nSources:\n- https://developers.openai.com/api/docs/models/gpt-realtime-translate\n- https://developers.openai.com/api/docs/pricing\n- https://developers.openai.com/api/docs/changelog","page_url":"https://postcutoff.com/m/gpt-realtime-translate/","standing":{"kind":"speech and audio","newer_count":57,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"gpt-audio-1-5","name":"GPT-Audio-1.5 (and gpt-audio / gpt-audio-mini)","org":"OpenAI","released":"2026-02-23","page_url":"https://postcutoff.com/m/gpt-audio-1-5/"},"after":{"id":"gpt-realtime-2-1","name":"GPT-Realtime-2.1","org":"OpenAI","released":"2026-07-06","page_url":"https://postcutoff.com/m/gpt-realtime-2-1/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}