TheFluxTrain
Sign in
All models
audio

Multilingual STS v2

Multilingual STS v2 changes voice identity on an existing audio track while keeping timing and performance.

Quick answer: ElevenLabs Multilingual STS v2 converts speech-to-speech voice identity on TheFluxTrain.

How to use

  1. Open the Multilingual STS v2 page on TheFluxTrain.
  2. Upload the audio track to drive speech or performance.
  3. Click Generate. Sign in if you are not already logged in — credits are used only when generation starts.
  4. Preview the result on this page, then reuse it in other TheFluxTrain studios if needed.

Capabilities

  • Convert an existing voice recording into another voice
  • Keep timing and performance while changing identity
  • Useful for localization, casting tests, and avatar audio

You can draft prompts on this page before signing in. Uploaded media and generation requests are sent only when you start a run, and credits are charged for successful generation jobs.

Frequently asked questions

High-quality speech-to-speech conversion
You can open the page and draft a prompt without signing in. TheFluxTrain asks you to sign in when you generate, and uses credits for the run.
Yes. Exploring the page is free. Starting a generation spends credits based on the model and settings you choose. The page shows an estimate before you run.
After you try it here, the same model is available in TheFluxTrain at /voice/change-voice, and in Flow Studio where that node family is supported.
This page accepts an audio track.
2 Credits