Gemini 3.8 Flash TTS and Flash-Lite TTS: voice models with custom voice creation
Google released two new TTS models: Flash TTS for creative voice generation and long-form audio, Flash-Lite for scale use cases like dubbing and voice agents; 100+ languages, custom voice generation and replication, fine-grained delivery control, via Google AI Studio and the Gemini API.
Why it matters
Custom voice creation plus detailed speech-delivery control in a first-party model, closing the gap with ElevenLabs-style voice cloning at Gemini API scale.
What you could build with it
A video-localization startup could build a one-click dubbing service for YouTube creators: translate scripts, then generate the creator's replicated voice in 100+ languages with matched delivery, without the per-minute voice-API costs of specialist providers.
Does it hold up?
Too early to judge — launched very recently; pricing, latency, and voice-quality claims have no third-party verification yet.
Built with Gemini 3.8 Flash TTS and Flash-Lite TTS
- Google Gemini 3.8 Flash TTS, Flash-Lite TTS with voice cloning roll outGadgets360 · Launch writeup covering both models, 100+ language support, custom voice generation, and AI Studio/API availability.
Learn more
First spotted on article: source.
More AI models
OpenAI publishes 722 AI-generated math manuscripts from an unreleased modelOpenAI released 722 mathematical manuscripts in 372 result families to GitHub under Apache-2.0, produced by an…models · JEV 0.74Mistral Large 4 (Le Chonk): 1.05T-param open-weight MoEMistral's new flagship: a 1.05T-parameter mixture-of-experts multimodal model with 49B active params and 1M-token…models · JEV 0.72ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71JetBrains Mellum 2.1: 12B MoE coding model trained for agentsJetBrains released Mellum 2.1, a 12B MoE model (2.5B active parameters, 128K context) under Apache 2.0, trained mainly…models · JEV 0.69DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.