Plain-text specification
Plain-text specification
ElevenLabs TTS v3 API
ElevenLabs TTS v3 is a text-to-speech model by ElevenLabs, available on the Venice API aselevenlabs-tts-v3. Requests are anonymized, so the provider never sees your identity.Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization.ElevenLabs TTS v3 API pricing
ElevenLabs TTS v3 specifications
How to use the ElevenLabs TTS v3 API
Send requests toPOST https://api.venice.ai/api/v1/audio/queue with "model": "elevenlabs-tts-v3" and your API key.ElevenLabs TTS v3 API FAQ
How much does the ElevenLabs TTS v3 API cost?
0.095 per minute of generated speech. Prices are in USD and can be paid in DIEM at parity.What is the ElevenLabs TTS v3 model ID?
Useelevenlabs-tts-v3 as the model parameter.Is the ElevenLabs TTS v3 API private?
ElevenLabs TTS v3 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.How many voices does ElevenLabs TTS v3 have?
20 voices, for exampleAria, Roger, Sarah. Output formats: mp3.Which endpoint does the ElevenLabs TTS v3 API use?
Queue a job withPOST /audio/queue, then poll /audio/retrieve for the result.Related models
- Qwen 3 TTS 1.7B API: $112.50 per 1M characters
- MiniMax Speech-02 HD API: $125.00 per 1M characters
- Qwen 3 TTS 0.6B API: $87.50 per 1M characters
- ElevenLabs Multilingual v2 API: $115.00 per 1M characters