Models / Voice
Gemini 3.8 Flash TTS
By Google, in Claude, ChatGPT, Cursor, Claude Code, and the API.
Clear, natural voiceovers from Google for about half the credits of ElevenLabs, with 30 voices of its own. Third in blind speech tests.
- Made by
- Type
- Voice
- Price band
- Budget
- Blind tests
- #3 on Artificial Analysis's text-to-speech arena, September 2026
- Voices
- 30 preset voices
- Model id
- gemini-3.8-flash-tts
Ask for it by name
Your AI uses the default for voice unless you name another. Say Gemini 3.8 Flash TTS and it uses this one.
youWrite a 20-second welcome for our podcast and record it with Gemini 3.8 Flash TTS.
A Studio month (3,000 credits) covers about 430 minutes of speech with Gemini 3.8 Flash TTS, or a mix with any other model. See plans.
Voices
- Kore — firm (default)
- Zephyr — bright
- Puck — upbeat
- Charon — informative
- Fenrir — excitable
- Leda — youthful
- Orus — firm
- Aoede — breezy
- Callirrhoe — easy-going
- Autonoe — bright
- Enceladus — breathy
- Iapetus — clear
- Umbriel — easy-going
- Algieba — smooth
- Despina — smooth
- Erinome — clear
- Algenib — gravelly
- Rasalgethi — informative
- Laomedeia — upbeat
- Achernar — soft
- Alnilam — firm
- Schedar — even
- Gacrux — mature
- Pulcherrima — forward
- Achird — friendly
- Zubenelgenubi — casual
- Vindemiatrix — gentle
- Sadachbia — lively
- Sadaltager — knowledgeable
- Sulafat — warm
From your own code
The same key your assistant uses works as a bearer token. See the docs.
curl https://getstudiopass.com/v1/generations \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"modality":"voice","model":"gemini-3.8-flash-tts","text":"Welcome to the show."}'