Gemini 3.5 Transcribe
Model Information
| Slug | gemini-3-5-transcribe |
|---|---|
| LLMs.txt | View |
| Release Date | September 25, 2026 New |
Organization
| Name | |
|---|---|
| Website | https://gemini.google.com/ |
Model Description
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 can be up to one hour, or 30 minutes when timestamps or diarization are enabled.
Available at 2 Providers
| Provider | Type | Model Name | Original Model | Input ($/1M) | Output ($/1M) | Free | Actions | |
|---|---|---|---|---|---|---|---|---|
|
OpenRouter |
Chat
Code
|
Gemini 3.5 Transcribe
|
google/gemini-3.5-transcribe
|
$2.00 | $12.00 | ||
|
Vercel AI Gateway |
Gemini 3.5 Transcribe
|
google/gemini-3.5-transcribe
|
$2.00 | $12.00 |