Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation. Prices are the providers' own, billed 1:1 with no markup β the router sends each request to the cheapest available offer.
| Provider | Model id | Price | vs cheapest |
|---|---|---|---|
| fal.ai | fal-ai/gemini-3.1-flash-tts | $0.0000 | +null% |
| Replicate | google/gemini-3.1-flash-tts | $0.1000 | +null% |
| Atlas Cloud | google/gemini-3.1-flash-tts | $0.1500 | +null% |
Routing Gemini 3.1 Flash TTS through fal.ai instead of the most expensive provider on this page saves 100% per generation β automatic on ElliSekiz.
curl -X POST https://ellisekiz.ai/api/v1/generations \
-H "Authorization: Bearer esk_..." \
-H "Content-Type: application/json" \
-d '{
"model": "google-gemini-3.1-flash-tts",
"prompt": "your prompt"
}'Omit provider and the cheapest offer wins; add it to pin one. Full reference in the docs.