Gemini 3.1 Flash TTS is Google's newest and most expressive voice on Ganabgen AI, with 30 voices, two-speaker dialogue, and inline audio tags.
Gemini 3.1 Flash TTS is Google's newest speech model on Ganabgen AI. Write a script, pick one of 30 voices (or an OpenAI-style alias like nova or alloy), and optionally pin a language. Inline tags such as [whispering], [excited], and [laughing] are performed rather than spoken.
Pricing is usage-based via dry-run and typically starts at 1 credit for a short clip. Two-speaker dialogue is supported with a maximum of two distinct voices. Pair it with Video Studio when you need a talking-head pass after the voiceover is locked.
Siblings: [Gemini 2.5 Flash TTS](/audio/gemini-2-5-flash-tts) and [Gemini 2.5 Pro TTS](/audio/gemini-2-5-pro-tts). Family guide: [Gemini TTS on Ganabgen AI](/blog/gemini-tts).
Generate with Gemini 3.1 Flash TTS by Google DeepMind on Picturesque. Browse all audio models.
| Credits | 1 credits |
|---|
Short clips typically start at 1 credit. Longer tagged scripts scale via dry-run.
Write [whispering], [excited], [laughing], [sighs], [sarcastic], or [calm] in the script. Gemini 3.1 Flash TTS performs the mark instead of speaking the word.
Same 30-voice catalog and two-speaker cap. 3.1 Flash is the only Gemini TTS route on Picturesque built for inline performance tags.
No. Cloning stays on ElevenLabs TTS.
Open Gemini 3.1 Flash TTS in Audio Studio. Family guide: Gemini TTS on Picturesque.
Explore more on Picturesque: Home, AI Image Generator, AI Video Generator, AI Audio Studio, Edit & Upscale, Motion Control, Director, Cinematic ad skill, UGC ad skill, Guides & Tutorials, FAQ, Explore, Pricing, Referral program, MCP. Resources: Blog.
Legal & policies: Terms, Privacy, Refunds, Delivery, Content policy, Cookies.