Gemini 3.8 Flash TTS 🧠 Model Paid

What it is

Gemini TTS is Google's speech generation line in the Gemini API. On 23 September 2026 Google launched two new models. Gemini 3.8 Flash TTS is built for top quality and directed performances. Gemini 3.8 Flash-Lite TTS is built for high-volume dubbing and agents. Both take natural-language direction for delivery and replace the earlier 3.1 Flash and 2.5 Pro TTS previews.

Key features

• Over 100 languages, with regional varieties such as Quebec French and Scots English
• 30 core studio voices plus a library of 2,000+ ready-made voices
• Custom voices designed from a text description
• Voice replication from a 30-second sample, with a verified consent recording
• Two-speaker dialogue and line-by-line delivery direction

Where you can use it

The Gemini API and Google AI Studio. Enterprise API access is coming soon. For end users, Flash TTS is rolling out in Gemini Notebook and Flash-Lite TTS in Google Vids. Neither is a separate listing in our directory yet.

Pricing and rights

API pricing per million tokens, valid until 31 December 2026: Flash TTS costs $0.50 input and $9 audio output. Flash-Lite TTS costs $0.50 input and $6 output. Both prices double from 1 January 2027. All audio carries an inaudible SynthID watermark. Voice replication needs a spoken consent recording from the voice owner, and it is not offered in Illinois, Texas, the EEA, the UK, Switzerland or India.

Who it is for

Developers and media teams producing narration, dubbing or multi-voice content at scale, especially in many languages.

Verdict

Gemini 3.8 Flash TTS combines a huge voice library, broad language coverage and strong consent safeguards. It is brand new, prices double in January 2027, and cloning is blocked in several major markets.