Model Metadata
- type
- transcription
- name
- GPT Realtime Whisper
- description
- Streaming speech-to-text model for low-latency transcript deltas from live audio
- family
- whisper
- open weights
- No
- release date
- 2026-05-07
- modalities
- input: audio/pcm, audio/pcmu, audio/pcma; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: Yes; top_p: Yes; top_k: No
- limit
- context: 16,000; output: 2,000
Provider Variants 2
OpenAI gpt-realtime-whisper
Context 16,000 · Output 2,000
- type
- transcription
- name
- GPT Realtime Whisper
- description
- Streaming speech-to-text model for low-latency transcript deltas from live audio
- family
- whisper
- open weights
- No
- release date
- 2026-05-07
- modalities
- input: audio/pcm, audio/pcmu, audio/pcma; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: Yes; top_p: Yes; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 16,000; output: 2,000
- id
- gpt-realtime-whisper
- canonical id
- openai/gpt-realtime-whisper
- last updated
- 2026-05-07
- api
- realtime: base_url: https://api.openai.com/v1; sdk: aisdk: @ai-sdk/openai
vercel openai/gpt-realtime-whisper
Context 16,000 · Output 2,000
- type
- transcription
- name
- gpt-realtime-whisper
- description
- Streaming speech-to-text model for low-latency transcript deltas from live audio
- family
- whisper
- open weights
- No
- release date
- 2026-05-07
- modalities
- input: audio/pcm, audio/pcmu, audio/pcma; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: No; top_p: No; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 16,000; output: 2,000
- id
- openai/gpt-realtime-whisper
- canonical id
- openai/gpt-realtime-whisper
- last updated
- 2026-05-07
- api
- transcriptions: base_url: https://ai-gateway.vercel.sh/v4/ai; sdk: aisdk: @ai-sdk/gateway