OpenAIAudio matchupSpeech to text
GPT-Live-Transcribevs.GPT-Realtime-Whisper
Which model is better?
GPT-Live-Transcribe is slightly ahead in independent tests, but the lead is not certain.
Independent testsArtificial Analysis
GPT-Live-Transcribe0 of 1
GPT-Realtime-Whisper0 of 1
Popularityout of 100
GPT-Live-Transcribeahead39
GPT-Realtime-Whisper34
Weights and access
GPT-Live-Transcribeproprietary
GPT-Realtime-Whisperproprietary
Priceverbatim from the provider
GPT-Live-Transcribe$0.017 per audio minute
GPT-Realtime-Whisper$0.017 per audio minute
Pick GPT-Live-Transcribe for
leaning Artificial Analysismore popular
Pick GPT-Realtime-Whisper for
No clear edge
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Artificial Analysis
GPT-Live-Transcribe slightly aheadArtificial Analysis AA-WER Streaming (final transcription)
GPT-Live-Transcribe3.9 %
GPT-Realtime-Whisper4.9 %
lower is better, as of October 15, 2026
Source · latest October 15, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| GPT-Live-Transcribe | GPT-Realtime-Whisper | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | OpenAI | OpenAI |
| Status | Active | Active |
| Released | July 28, 2026 | n/a |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | $0.017 per audio minute | $0.017 per audio minute |
| Popularity (out of 100) | 39 | 34 |
More comparisons with GPT-Live-Transcribe and GPT-Realtime-Whisper
GPT-Live-Transcribevs.FluxGPT-Live-Transcribevs.Gemini 3.5 Transcribe LiveGPT-Realtime-Whispervs.FluxGPT-Realtime-Whispervs.Nova-3GPT-Realtime-Whispervs.Gemini 3.5 Transcribe LiveGPT-Live-Transcribevs.Scribe v2 RealtimeGPT-Realtime-Whispervs.Scribe v2 RealtimeGPT-Live-Transcribevs.Voxtral Mini Transcribe RealtimeGPT-Realtime-Whispervs.Voxtral Mini Transcribe Realtime