Google: Gemini 3.5 Transcribe
- by google
- google/gemini-3.5-transcribe
Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...
What the numbers mean
- Context window98,304 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 74,000 words, or 147 pages.
- Max output32,768 tokens
- The longest single reply it can write: about 25,000 words.
- Input price$2 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$12 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiesaudio in, transcription out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.