Details
- Google is launching Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two text-to-speech models designed for expressive voice generation.
- The models support custom voice creation across more than 100 languages and offer over 2,000 ready-to-use voices.
- Developers can direct back-and-forth conversations and control vocal delivery line by line, giving users finer control over tone and performance.
- Both models are rolling out to Google AI Studio and the Gemini API for developers.
- Gemini 3.8 Flash TTS is being added to Gemini Notebook, while Gemini 3.8 Flash-Lite TTS is coming to Google Vids.
- Both models are scheduled to arrive in Gemini Enterprise soon.
- Google describes Flash-Lite as optimized for high-throughput, low-latency, cost-efficient conversational speech; its published pricing lists lower audio-output costs than Flash TTS.
- Google says Flash TTS ranked first on Hume AI’s Voice Design Benchmark and that both models performed strongly in voice-quality evaluations, though those results are vendor-reported.
Impact
The launch expands Google’s competition in generative voice by combining multilingual coverage, selectable voices and programmable dialogue control in its developer and productivity products. Flash-Lite’s lower-cost, lower-latency positioning could make synthetic speech more practical for high-volume applications, while Flash TTS targets richer character and delivery control. Availability across AI Studio, Gemini, Notebook, Vids and Enterprise also gives Google multiple distribution channels rather than relying on a standalone voice product.
