Context 131,072 · Output 65,536
- type
- transcription
- name
- Gemini 3.5 Transcribe Live
- description
- Speech transcription model for accurate audio-to-text and captioning workflows
- family
- gemini
- open weights
- No
- release date
- 2026-08-26
- modalities
- input: audio/pcm; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; cache: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 131,072; output: 65,536
- id
- gemini-3.5-transcribe-live
- canonical id
- google/gemini-3.5-transcribe-live
- last updated
- 2026-08-26
- api
- bidi-generate-content: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google