Voice model
Eleven v3 API
Eleven v3 is a text to speech model from ElevenLabs, live in the voice lane of the Corent catalog. It turns text into finished audio on POST /v1/audio/speech, with the exact charge on every response.
Pin it by name, or let the router earn it.
You pick
POST /v1/audio/speech{ "text": "Welcome to Corent.", "model": "corent-eleven-v3"}
Direct access runs Eleven v3 and no other model. No substitution, flat cost-plus, billed only on success, and the receipt names the model you pinned.
The router picks
POST /v1/audio/speech{ "text": "Welcome to Corent."}
Leave the model out and the speech tier serves the request: the router picks a live model and the receipt names the tier.
One key, one request.
curl -X POST https://api.corent.tech/v1/audio/speech \ -H "Authorization: Bearer $CORENT_API_KEY" \ -H "Content-Type: application/json" \ -d '{"text": "Welcome to Corent.", "model": "corent-eleven-v3"}'
The response carries the result and a receipt: the model that served you and the exact cost in cents. Full request and response shapes are in the docs.
Eleven v3, as the API serves it today.
- Pin by name
corent-eleven-v3- Modality
- Voice
- Endpoint
- POST /v1/audio/speech
- Lab
- ElevenLabs
- Quality
- 8.2 out of 10, Corent's score
- Status
- Live
These fields come from the live catalog, the same GET /v1/models payload the full model ledger prints, so they can never drift from what the API actually serves.
Common questions
Does Eleven v3 have an API?
Yes. Eleven v3 is served through the Corent API on POST /v1/audio/speech. Pin the exact name corent-eleven-v3 and you get that model or nothing: no substitution, and a failed generation is never billed. One Corent key covers it alongside every other model in the catalog.
How much does Eleven v3 cost via Corent?
Corent does not publish a per-model rate card. Direct access is flat cost-plus, you are billed only on success, and every response carries the exact charge on its receipt. Tier prices are public on the pricing page at corent.tech/pricing.
Do I have to pick Eleven v3?
No. Send a tier instead of a model and the router reads each prompt, picks the best live model at that moment, and reroutes on failure. Pinning corent-eleven-v3 is for when you want exactly this model on every request.
Related models
Every one of them runs on the same key and the same endpoint as Eleven v3, and the full model ledger lists the whole catalog.
Run Eleven v3 in your next request
One key opens the whole catalog: pin Eleven v3, or name a tier and never pick a model again. Start with $5 in prepaid credits.
Get an API key