JetBrains' open 12B mixture-of-experts coding model with 2.5B parameters active per token under Apache 2.0
Gemini 3.8 Flash TTS
New· 4Google's text-to-speech model for directed, expressive speech, with voice design from a written description and 130 languages
About Gemini 3.8 Flash TTS
Google's Gemini 3.8 Flash TTS is a text-to-speech model built for directed, expressive audio rather than flat narration. Google announced it on its blog on 23 September 2026, and the Gemini API changelog lists general availability a day earlier.
Designing and directing a voice
A plain-language description of how a voice should sound is enough to design one, and each line can be given its own direction. Scenes with two speakers are produced natively, and long recordings are supported. Google counts over 2,000 ready-made voices. Subject to a consent check, a voice can also be cloned from a 30-second sample, except where replication is withheld: Texas, Illinois, India, Switzerland, the EEA and the UK. Output carries Google's SynthID watermark.
Limits and supported features
Google's model page gives 130 languages, with input capped at 8,192 tokens and output at 16,384. It supports batch processing, caching and flex or priority inference, but not function calling, structured output or grounding. One second of audio counts as 25 tokens.
Pricing structure and usage terms
On the paid tier, audio output is billed per million tokens, and Google's published rates apply only through 31 December 2026. Every rate doubles on 1 January 2027, so any budget built on the launch price covers about three months. On data use, the pricing page says free-tier traffic may help improve Google's products while paid-tier traffic does not.
How it has ranked
Artificial Analysis's independent Provider Voice Arena had the model in second place on 24 September 2026, though arena ratings move as votes arrive. Google separately claims first place on Hume AI's Voice Design Benchmark and top positions in several languages; those are its own readings of the tests.
TrustList summary
Google's Gemini 3.8 Flash TTS turns written text into speech and is built for production audio work. A voice can be shaped from a plain-language description of how it should sound, and each line's delivery can be directed.
On Artificial Analysis's Provider Voice Arena it ranked second when read on 24 September 2026, and arena ratings shift as votes arrive.
What Gemini 3.8 Flash TTS does
- Voice design: builds a voice from a written description.
- Directed delivery: sets how each line is spoken, and generates two-speaker scenes natively.
- Long-form audio: supports long-form audio output.
- Voice replication: copies a voice from a 30-second sample after a consent check, except in the UK, the EEA, Switzerland, India, Illinois and Texas.
- Ready-made voices: more than 2,000 built-in voices to choose from.
Key facts
- Languages: 130 languages.
- Input limit: 8,192 tokens.
- Output limit: 16,384 tokens.
- Not supported: function calling, structured output or grounding.
- Watermark: output carries Google's SynthID watermark.
- Free-tier data: Google's pricing page says free-tier use may be used to improve its products, while paid-tier use is not.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
Gemini 3.8 Flash TTS launches
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 9/24/2026
Request a demo or quote from Gemini 3.8 Flash TTS
Reviews
Write the first review of Gemini 3.8 Flash TTS
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about Gemini 3.8 Flash TTS.
Gemini 3.8 Flash TTS alternatives
Similar listings buyers compare against this one.
Liquid AI's open-weight decision model, giving yes or no, choice or score answers from text and images
Google's open multimodal embedding model that maps text, images, audio and video into one vector space, under Apache 2.0
Open-source 2B decision model from AWS's Strands Agents project that picks options and returns scores with a reliability figure
Microsoft AI's text-to-speech model for keeping one voice across 23 languages, with voice cloning from short audio
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.