Gemini 3.8 Flash TTS
Google's TTS with a 2,000-voice library — design a voice from a text prompt, clone one from a 30-second sample.
About
Gemini 3.8 Flash TTS, shipped September 22, 2026 per the Gemini API changelog (press coverage dated it the 23rd), is Google's text-to-speech refresh. The headline is the voice library, which grows from 30 voices to more than 2,000. It covers 100+ languages, designs a voice from a text prompt, clones a voice from a 30-second sample, and handles two-speaker scenes, laughs, and sighs, with inline tags like [sigh] rendered as sounds. Output is marked with SynthID.
One limit decides a lot of plans: voice cloning is unavailable in the EEA, the UK, Switzerland, India, Illinois, and Texas. If your team or speaker sits in one of those places, the cloning path is closed on Google regardless of quality.
A Flash-Lite TTS tier shipped the same day for bulk workloads. No independent quality benchmarks have been published; adoption in third-party voice studios within days of launch is the closest thing to a real-world check.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
No independent quality benchmarks found.
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Release facts (September 22, 2026; 2,000+ voices; 100+ languages; prompt-based voice design; 30-second cloning; SynthID marking) confirmed by Google's API changelog and independent voice-studio reporting. Docked for: (1) no independent quality benchmarks; (2) voice cloning is geo-restricted in the EEA, UK, Switzerland, India, Illinois, and Texas; (3) proprietary with no weights.
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 8.0/10
- Maintenance · recency, releases, issue load
- 9.0/10
- Openness · license + docs
- 3.0/10
- Manual review · sanity read + red-flag check
- 8.0/10
- · Adoption 8: shipped Sept 22, 2026 per API changelog; adopted into third-party voice studios within days
- · Maintenance 9: Google Gemini API changelog maintained; Flash-Lite tier alongside
- · Openness 3: proprietary API-only, no weights
- · Manual 8: 2,000+ voice library, 100+ languages, SynthID marking verified; cloning geo-restrictions documented (EEA/UK/CH/IN/IL/TX)