feat: add Gemini 3.1 flash TTS support, implement streaming response …

[thorwebdev]

…handling, and include new examples and tests.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[devin-ai-integration]

Devin Review found 1 new potential issue.

[devin-ai-integration]

🚩 Default model changed to 'gemini-3.1-flash-tts-preview' — breaking change for existing users

The DEFAULT_MODEL was changed from "gemini-2.5-flash-preview-tts" to "gemini-3.1-flash-tts-preview". Any existing code that instantiates GeminiTTS() without explicitly passing model= will now use a different model. This is a behavioral change that could affect output quality, latency, or pricing. Worth noting in changelog/release notes. The old model is still available in the GEMINI_TTS_MODELS literal type, so users can pin to it explicitly.

---

Was this helpful? React with 👍 or 👎 to provide feedback.