GPT-Transcribe
Speech and audio
gpt-transcribe
$0.0045 per minute
GPT-Live-Transcribe
Streaming sibling of gpt-transcribe for captions, voice agents and meeting notes.
Model idgpt-live-transcribe
Price$0.017 per minute
Checked29 September 2026
Where it stands
40newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from OpenAI
- GPT-Live 18 Jul 2026
- After it from OpenAI
- GPT-Live-1.115 Oct 2026
- Weights
- Closed weights; access is hosted only.
How to call it
Where to use GPT-Live-Transcribe, with its model id.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| OpenAI API | gpt-live-transcribe |
v1/realtime/transcription_sessions (Realtime transcription session over WebSocket/WebRTC) |
developers.openai.com |
Pricing
| Per minute | $0.017 |
|---|
As published: “per minute of realtime audio (USD)”.
Source: developers.openai.com, checked 29 September 2026.
Specs
- Input
- Audio and text
- Output
- Text
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 28 July 2026
- Status
- Current
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Low-latency streaming transcription with context hints
Streams transcript deltas with tunable latency and accepts unstructured context, keyword hints and multiple language hints.
Recommended replacement for Whisper streaming use
Found after launch
Named (with gpt-transcribe) as the replacement for whisper-1 and gpt-4o-(mini-)transcribe(-diarize), which shut down 2027-02-26.
Notes
Released with gpt-transcribe (file transcription, $0.0045/min) on 2026-07-28 per the changelog. Languages and latency figures not published on the docs page.
Sources: