Gemini 3.5 Transcribe
Turn live and recorded speech into precise, formatted text
About
Gemini 3.5 Transcribe is Google's speech-to-text model for intelligent voice applications. Developers can stream audio with sub-second latency or process recordings with speaker attribution and word-level timestamps for voice agents, captions, meetings, call analysis, and other transcription workflows.
Data Analysis
Report this product
Related products
Speko
paidRoute voice AI sessions to models measured by language and cost
OpenComputer
freemiumDeploy durable AI agents with a real Linux computer per session
