Model Metadata
- v2 only
- Yes
- type
- transcription
- name
- Gemini 3.5 Transcribe
- description
- Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary
- family
- gemini
- open weights
- No
- release date
- 2026-08-26
- modalities
- input: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 98,304; output: 32,768
Provider Variants 3
Google gemini-3.5-transcribe
Context 98,304 · Output 32,768
- type
- transcription
- name
- Gemini 3.5 Transcribe
- description
- Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary
- family
- gemini
- open weights
- No
- release date
- 2026-08-26
- modalities
- input: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm; 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: 98,304; output: 32,768
- id
- gemini-3.5-transcribe
- canonical id
- google/gemini-3.5-transcribe
- last updated
- 2026-08-26
- api
- transcriptions: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google; opencodeai: @opencode/ai/protocols/google-transcription
OpenRouter google/gemini-3.5-transcribe
Context 98,304 · Output 32,768
- type
- transcription
- name
- Gemini 3.5 Transcribe
- description
- Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary
- family
- gemini
- open weights
- No
- release date
- 2026-08-26
- modalities
- input: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 98,304; output: 32,768
- id
- google/gemini-3.5-transcribe
- canonical id
- google/gemini-3.5-transcribe
- last updated
- 2026-08-26
- api
- transcriptions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/protocols/openai-transcription
vercel google/gemini-3.5-transcribe
Context 98,304 · Output 32,768
- type
- transcription
- name
- Gemini 3.5 Transcribe
- description
- Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary
- family
- gemini
- open weights
- No
- release date
- 2026-08-26
- modalities
- input: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm; 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: 98,304; output: 32,768
- id
- google/gemini-3.5-transcribe
- canonical id
- google/gemini-3.5-transcribe
- last updated
- 2026-08-26
- api
- transcriptions: base_url: https://ai-gateway.vercel.sh/v4/ai; sdk: aisdk: @ai-sdk/gateway