Tavus Video Generation is a separate product from the Conversational Video Interface. It is designed solely for generating AI videos - you provide a script and a Replica, and Tavus produces a finished video. There is no real-time interaction involved. At a glanceDocumentation Index
Fetch the complete documentation index at: https://docs.tavus.io/llms.txt
Use this file to discover all available pages before exploring further.
- What it does — Turn a written script plus a replica into a finished, downloadable video (batch-style, not a live call).
- Replicas — Use stock replicas out of the box or train a custom replica for your own likeness.
- Next step — Video quickstart or the Developer Portal.
Key features
Stock & custom replicas
Get started instantly with stock replicas, or train a custom replica with just two minutes of video.
Photo-realistic replicas
In-house models deliver lifelike results using advanced techniques for both stock and custom replicas.
Languages
Generate videos in 42 supported languages with your real voice.
Bring Your Own Audio
Use default TTS or upload your own audio for video generation.
Token usage is based on video duration. Output can vary slightly even with the same script and Replica.