Gemini 2.5 Flash TTS — HYR Studio's Voice Layer
Every narrated video and voiceover, in 30 languages, from one voice engine.
Gemini 2.5 Flash TTS is Google's text-to-speech model. HYR Studio uses it for all voiceover and narration — slide narration in video renders, the AI Infographic Narrator, and spoken versions of written assets in 30 languages.
Provider
Google DeepMind
How HYR Studio uses Gemini 2.5 Flash TTS
Whenever an asset needs a voice, HYR Studio routes Gemini 2.5 Flash TTS: per-slide narration in slideshow-to-video, the Infographic Narrator zoom-and-voiceover renders, and Digital C-Suite agent voice output.
Capabilities
- Natural prosody text-to-speech
- Multilingual narration across 30 languages
- Per-slide narration in video pipelines
- Fast synthesis for interactive workflows
Output Types Powered
- Video narration
- Infographic narration
- Voiceover audio
- Agent voice output
Narration is generated in the same language and tone as the rest of the asset set, so a full campaign — deck, video, blog, and audio — sounds like one voice.