Gemini 3.8 Flash TTS and 3.8 Flash-Lite TTS
2026-09-23 · Publisher : Google · Domain : Artificial Intelligence
Google launches Gemini 3.8 Flash TTS and 3.8 Flash-Lite TTS, two text-to-speech models with voice creation by prompt, voice replication from 30 seconds of audio and a library of more than 2,000 voices.
What changes
- 3.8 Flash TTS: voice design from scratch through a natural-language description, more than 100 languages and dialects.
- 3.8 Flash-Lite TTS: low-cost version for dubbing, high-volume audio content and voice agents.
- Voice replication from a 30-second sample, with consent verification, SynthID and C2PA.
- Library of more than 2,000 voices, including regional variants (Mexican Spanish, Quebec French).
- Line-by-line direction of the vocal performance; voice remixing announced as coming.
### Specifications - Identifiers: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts (changelog of September 22, 2026). - Availability: Gemini API, AI Studio, Google Vids, Gemini Notebook. ### Pricing | Model | Text input / audio output (USD / 1M tokens), until 12/31/2026 | From 01/01/2027 | |---|---|---| | 3.8 Flash TTS | 0.50 / 9.00 | 1.00 / 18.00 | | 3.8 Flash-Lite TTS | 0.50 / 6.00 | 1.00 / 12.00 | Batch and Flex: half of these prices. Prices recorded from the current pricing page. ### Benchmarks No scores published in the post consulted. ### Key takeaways Synthetic voice becomes customizable and cloneable, with consent and traceability safeguards.
Links
Tags : Audio, Google, Gemini, TTS, Voix