Eleven V4
Neural Network
Eleven V4 is an ElevenLabs speech synthesis model for text-to-speech with expressive intonation and support for over 90 languages.
Specifications
- Input
- text
- Output
- audio
- Number of voices
- 6
Prompt cost
(per 1M tokens)
How it works Eleven V4?
Eleven V4 is a speech synthesis model from ElevenLabs: it turns text into audio, focusing on generation speed and emotional voice expressiveness. It supports over 90 languages, allowing you to handle tasks for different audiences in a single pipeline. In BotHub, the model works without a VPN or foreign card: you pay with a Russian card in rubles based on usage, with no subscription, and unused balances do not expire. Over 250 other neural networks are available in the same window, so you can prepare your script in one model and send it directly to Eleven V4 for voiceover without switching services. For product tasks, there is a unified OpenAI-compatible API, and companies can access contracts, invoices, and electronic document management. Use cases are simple: voiceovers for videos, reels, and training courses; audio versions of articles, newsletters, and podcasts; voices for bots, assistants, and auto-responders; character lines for games and interface prototypes; and quick rough drafts to hear the text before recording with a studio voice actor.Frequently asked questions about Eleven V4
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.
Eleven v4 by ElevenLabs is a speech synthesis model: you provide text, and you get audio output. It is suitable for audiobooks, podcasts, videos, training courses, voice interfaces, and prototypes. Up to 10,000 tokens are processed per request, so you don't need to split long fragments manually.
You get an audio track with synthesized speech, ready for editing or publishing. Specific characteristics depend on request parameters and your integration, so refer to the values in the technical header of the page. The result can be downloaded immediately or retrieved via API and inserted into your pipeline.
Our data does not indicate a separate reasoning mode for Eleven v4, and it is usually not needed for speech synthesis: the model's task is to voice ready-made text. If you need reasoning and analysis, prepare the text using a text model in BotHub, and assign the voiceover to Eleven v4.
Function calling and structured JSON output are not indicated in our data — Eleven v4 responds with audio, not text structures. Build the schema using a text model, and connect Eleven v4 as a voiceover step: BotHub's unified OpenAI-compatible API allows you to do this without rewriting the integration.
Accepting anything other than text is not indicated in our data: the workflow is that you send text and receive audio. If you need to analyze an image, recording, or video, switch to a suitable model in the same BotHub window and send its result for voiceover.
We do not have confirmed data on the language set of Eleven v4, so we won't make any promises — run a short fragment of your text and evaluate the sound yourself. BotHub itself is fully in Russian: access without VPN or foreign cards, payment with Russian cards.