Streaming via streamGenerateContent (and stream: true in the Interactions API) is now supported for the gemini-3.1-flash-tts-preview model. To learn more, see the Text-to-Speech guide.
Fetched June 19, 2026
Added Gemini 3.1 Flash TTS support with streaming response and AssemblyAI streaming mode with latency/accuracy preset. Also adds Soniox STT…
LiveKit · Agents (Python)Added support for Gemini text-to-speech (speech) models in the Google Vertex provider.
Vercel · AI SDKAdds audioOffset and interimInputTranscription to Live API components, plus LanguageAuto, LanguageHints, and adaptationPhrases to AudioTran…
Google · GeminiGoogle Vids AI avatars grow from 23 to 53 preset styles spanning photorealistic, 3D cartoon, and graphic novel looks, with support expandin…
Google · Workspace
