OpenAI says context lifts GPT-Live-Transcribe accuracy to 44.6% on a new ASR benchmark
OpenAIDevs · x · 2026-07-29
OpenAI says builders can improve live transcription by providing:
- free-form context about the recording
- keywords for names and domain-specific terms
- expected input languages
- earlier transcribed turns as context
On its new Context Aware Automatic Speech Recognition benchmark, GPT-Live-Transcribe’s semantic accuracy rose from 38.5% without free-form context to 44.6% with it.
OpenAI also shared benchmark results:
- Common Voice, 22 languages: GPT-Live-Transcribe WER 19.70% vs 20.33% for GPT-Realtime-Whisper-1.
- Real-World Audio Recording, 9 languages: GPT-Live-Transcribe WER 9.60% vs 11.65% for GPT-Realtime-Whisper-1.
More from Models
- DeepSeek ships V4.1-Flash-1017: open weights, 1M context, claims Opus 5-level coding — CurieuxExplorer · 2026-10-17
- Elorian launches Glimpse, an Astra-level visual reasoning model at 17x lower cost — CurieuxExplorer · 2026-10-17
- Reflection AI open-sources Beam weights under Apache 2.0 with Mirror CLI harness — CurieuxExplorer · 2026-10-17
- Generative UI 101: Building Live Interfaces with Agents on Opus 5.5 and Rivals — EXM7777 · 2026-10-17
- OpenAI's new $500 tier and $200 plan throttling are driving power users away — cybrstg · 2026-10-17
- DeepSeek shows rapid vision gains: agent self-checks screenshots to build 3D scene — cedric_chee · 2026-10-17