Eleven v3
Eleven v3 for Speech generation.
Explore Eleven v3 for Speech generation through the unified API. Supported interfaces and current availability are shown below.
- Speech generation
Model details
- Context window
- 5K tokens
- Max output
- —
- Input
- Text
- Output
- Audio
- Capabilities
- —
- Interfaces
- Speech generation
Pricing
Prices use the units shown below. No gateway fees. Usage, size and model options may affect the total.
| Metric | Price |
|---|---|
| / 1M characters | $110 |
Why teams pick it
- Eleven v3 for Speech generation.
Call Eleven v3
Eleven v3 answers on the API below — pick the one your code already speaks and just swap in your Inferray key.
/v1/audio/speechSpeech generation · openai SDK or plain HTTP
curl https://api.inferray.com/v1/audio/speech \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
-d '{
"model": "eleven-v3",
"input": "Hello, welcome."
}' \
--output speech.audioMore from ElevenLabs
Questions about this model
- Is there a free tier for Eleven v3?
- No. You add credit and pay Eleven v3's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
- Am I charged for failed requests?
- No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
- Is Eleven v3 included in Token Plans?
- No. Eleven v3 is pay-as-you-go only; Token Plans cover the other text models in the catalog.
- Does Eleven v3 support tool calling and vision?
- Eleven v3 takes text in and returns text.
- Is it the real Eleven v3?
- Yes. A request for eleven-v3 is answered by Eleven v3 from ElevenLabs, billed at its published list price. Inferray never substitutes a different or smaller model.