All models
audio generation
PreviewGemini 3.1 Flash TTS
Gemini 3.1 Flash TTS is Google’s preview text-to-speech model for controllable audio from exact text. It detects the spoken language automatically across more than 70 languages, and Google documents single-speaker and two-speaker output, natural-language direction for style, accent, pace, and tone, and 30 prebuilt voices; Gobostock keeps each voice tied to the engine it belongs to.
The audio tool calculates the final credit quote from the selected operation and output settings. The quote shown in the tool is the one you pay.
0:000:06
Audio paused
Best for
- Narration that must recite exact text
- Designed voices using Google’s prebuilt speaker catalog
Known limits
- The Gemini TTS endpoint is a preview model.
- Generated voices must remain bound to the Google runtime used to create them.
Capabilities
- Single-speaker and two-speaker text-to-speech
- Natural-language control over style, accent, pace, and tone
- 30 prebuilt Google voices with automatic language detection across 70+ languages
Inputs
- Exact script
- Prebuilt voice selection
- Optional style and delivery direction
Outputs
- Generated speech audio
Made on Gobostock
More from Gemini 3.1 Flash TTS
0:000:05
Audio paused
0:000:04
Audio paused
0:000:06
Audio paused
0:000:05
Audio paused
Watermarked previews
Compare