Skip to main content

ElevenLabs Multilingual v2 API

ElevenLabs Multilingual v2 is a text-to-speech model by ElevenLabs, available on the Venice API as elevenlabs-tts-multilingual-v2. Requests are anonymized, so the provider never sees your identity.Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy.

ElevenLabs Multilingual v2 API pricing

ElevenLabs Multilingual v2 specifications

How to use the ElevenLabs Multilingual v2 API

Send requests to POST https://api.venice.ai/api/v1/audio/queue with "model": "elevenlabs-tts-multilingual-v2" and your API key.

ElevenLabs Multilingual v2 API FAQ

How much does the ElevenLabs Multilingual v2 API cost?

115per1Mcharactersofinputtext,about115 per 1M characters of input text, about 0.095 per minute of generated speech. Prices are in USD and can be paid in DIEM at parity.

What is the ElevenLabs Multilingual v2 model ID?

Use elevenlabs-tts-multilingual-v2 as the model parameter.

Is the ElevenLabs Multilingual v2 API private?

ElevenLabs Multilingual v2 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 Multilingual v2 have?

20 voices, for example Aria, Roger, Sarah. Output formats: mp3.

Which endpoint does the ElevenLabs Multilingual v2 API use?

Queue a job with POST /audio/queue, then poll /audio/retrieve for the result.

Related models