Google launches Gemini 3.8 TTS: 2,000+ voices, voice cloning, 1m18s audio for 2.74 cents
rseroter · x · 2026-09-24
Google shipped two new text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, focused on low cost and multi-speaker conversation generation.
- Ships with 2,000+ preset voices plus custom voice cloning from a 30-second audio sample
- The API makes it easy to script full multi-character conversations, each with distinct voices and style instructions
- Simon Willison vibe-coded a bring-your-own-key TTS Playground with GPT-6 Astra, leveraging the Gemini API's open CORS policy; it supports single-voice narration and multi-speaker dialogues with shareable URLs
- Benchmark from his demo: 20 seconds to generate 1m 18s of audio on Flash TTS at a cost of 2.74 cents; the two-pelicans-debating script was written by Claude 4.5 Opus
Related event: Google Launches Gemini 3.8 Flash TTS with 30-Second Voice Cloning(27 posts)→
More from Multimodal
- H3-Image touts 16MP generation and realtime inference via 2-step LoRA on ZeroGPU — linoy_tsaban · 2026-11-12
- MiniMax H3 Image renders 4K portrait in half the time Seedream 5.5 takes for 2K — heyronir · 2026-11-12
- Endless screensaver of self-assembling quantum cryostats, made with Gemini 4 Carbon — hapticdata · 2026-11-12
- Apple's ADM 3 Cloud image model ranks #42 in editing and #85 in text-to-image on Artificial Analysis arena — ArtificialAnlys · 2026-11-12
- Adobe Firefly debuts Story Builder tool for streamlined visual storytelling — LudovicCreator · 2026-11-12
- Intangible 2.0 Launches as One AI Studio Unifying Image, Video and 3D Models — umesh_ai · 2026-11-12