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 v3 Conversational is a speech synthesis model: you send a text line or script, and receive a ready-made audio track. It is suitable for voicing dialogues, voice assistants and bots, videos, podcasts, and educational materials where natural conversational intonation is required.

You receive an audio track with synthesized speech. The model context is 5000 tokens, with the same amount allocated for a single response, so it is more convenient to break long scripts into individual lines and fragments. No additional file parameters are noted in our data.

A separate reasoning mode is not noted in our data, and it is usually not needed for speech synthesis: the model's task is to turn text into a spoken line, not to build logical chains. Prepare the semantic part with a text model, and entrust the voiceover to Eleven v3 Conversational.

There are no notes about function calling or structured JSON output in our data — this is expected for a model that outputs sound, not text structure. If you need functions and strict schemas, build a pipeline: a text model handles the logic, and this one performs the voiceover. All models are available via a unified OpenAI-compatible BotHub API.

Acceptance of files other than text is not noted in our data: the main scenario is to send text and receive audio. If you need to work with images or video recordings, switch to a multimodal model in the same BotHub window, and leave speech synthesis to this one.

We have no data on supported languages, so we will not promise anything specific — check it with your own text in BotHub. It's fast: access from Russia works without a VPN or foreign card, and payment is in rubles based on actual token usage.