Eleven Multilingual V2 IVC
Neural Network
Eleven Multilingual V2 IVC is an ElevenLabs speech synthesis model for voiceovers, audiobooks, and post-production in 29 languages.
Specifications
- Input
- audio
- Output
- audio
Prompt cost
(per 1M tokens)
How it works Eleven Multilingual V2 IVC?
Eleven Multilingual V2 IVC is an ElevenLabs speech synthesis model that sounds extremely close to a human voice: intonations, pauses, and emotional delivery are preserved in 29 languages, and the Instant Voice Cloning (IVC) mode allows you to obtain a specific timbre from a short sample. It is a working tool for voiceovers, audiobooks, and post-production where not just intelligibility, but the character of the voice matters. In BotHub, the model is available without a VPN or foreign card: you pay with a Russian card in rubles and only for what you actually generated, and unused tokens do not expire. Nearby, in one window, there are over 250 models, so you can assemble a video entirely without changing services, and connections and data are protected by AES-GCM encryption. For production, there is a unified OpenAI-compatible API, and for teams, there is a contract, invoice, EDO, and an admin panel with limits. It is most often used for voicing advertising and educational videos, recording audiobooks and podcasts, dubbing and replacing individual lines in post-production, as well as for voice interfaces and characters in games and applications.Frequently asked questions about Eleven Multilingual V2 IVC
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
This is a speech synthesis model from ElevenLabs: it takes audio as input and outputs audio. It is suitable for voiceovers for videos and podcasts, audiobooks, commercials, educational materials, and voice interfaces when you need a lively, natural-sounding voice based on an audio sample.
This model returns audio, not text. According to our data, 10,000 context tokens and the same amount on output are available, meaning you voice a fragment per request. Break long scripts or books into parts and stitch the results together.
In our data, step-by-step reasoning is not noted for this model — it is a voiceover tool, not an analysis tool. It is more convenient to delegate logic to a text model in BotHub: it prepares and proofreads the script, and Eleven Multilingual v2 turns it into an audio track.
Function calling and structured JSON are not noted in our data: you get audio as output, not a field schema. However, the model is available via the unified OpenAI-compatible BotHub API, so it is easy to integrate voiceover into your service or content processing pipeline.
Audio — yes, this is the main input: you provide a voice recording as a reference and get a voiceover in the same style. Images and video are not noted as input formats in our data, so use other models from the catalog for pictures and clips.
The model is claimed to be multilingual and is used specifically for multilingual voiceovers, but specific languages and pronunciation quality are not recorded in our data, so we will not promise specific figures. Test it with your own fragment: access from Russia is available without a VPN or foreign card, and payment is made with Russian cards.