What GEM-2.5-TTS is good at
Audio models create music, voice-overs or narration, billed per request.
Text-to-speech with 30 preset voices and 24 languages. Supports two-speaker dialogue and tone control in plain language. Good for ad voice-overs, audiobooks and long-form narration.
Good for
- Background music for videos
- Voice-overs and narration
- Audio for podcasts and short videos
Less suited for
- Articles or code: use a chat model
Code sample
How to call it will be in the docs. You can sign up and create an API key now; you will not need a new key when it opens.
What it costs, roughly
Estimated from the unit price above; you are charged per generation.
| 1 request1 × Rp 0 | Rp 0 |
| 10 requests10 × Rp 0 | Rp 0 |
| 100 requests100 × Rp 0 | Rp 0 |
Model status
Calls over the last 24 hours.
Related models
One API key calls them all; to switch, just change the model name.
Other Google models
GEM 3.1 TTSComing soonRp 20.304 / Rp 405.776
GEM 3.8 FlashRp 985 / Rp 4.927
GEM 4 ArgonRp 18.811 / Rp 94.054
GEM 3.5 FlashRp 9.435 / Rp 56.432
Banana 2.1 Per CallComing soonRp 314 per image
GEM 3.1 ProRp 12.541 / Rp 75.243
Alternatives at a similar price
Hailuo Voice Clone 2.8Coming soonRp 1.552.637 / Rp 0
Doubao TTS 2.0Coming soonRp 1.791.504 / Rp 0