Model
Gemini 3.5 Transcribe Live
Speech transcription model for accurate audio-to-text and captioning workflows
1 providers · 1 listingsreleased closed weights
Compare providers (sorted by listed input price)
Recent changes
Changelog →- new modelvia vercel · Aug 27, 2026
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.