DEDUPEDVoice cloning. The app clones the voice in whatever reference clip you upload, so use voices you may use.
platform. The --share flag exposes your app through a public link.
Who it is forA creator who wants a UI rather than flags.
The problemCommand line flags are awkward for iterating on takes.
The outcomeA local web app where you can produce and compare takes.
What you need first
- Python 3.10 or newer, for example a conda env created with `conda create -n f5-tts python=3.11`
- PyTorch and torchaudio matched to your device, plus FFmpeg
- A reference WAV clip of the voice you want, and its transcript if you do not want ASR to transcribe it
- A GPU for comfortable speed; the published benchmarks use a single L20
Steps
- Install the package with
pip install f5-ttsas in the installation section - Launch the app with
f5-tts_infer-gradio - Choose the port and host with
f5-tts_infer-gradio --port 7860 --host 0.0.0.0, or create a public link withf5-tts_infer-gradio --share - Use the Multi-Style and Multi-Speaker Generation and Voice Chat features listed in the README
Prompt for your agent
With SWivid/F5-TTS, start the Gradio app on port 7860 and walk me through producing a two speaker dialogue from <my script>.
Caveat. Voice Chat in the app is powered by Qwen2.5-3B-Instruct, which is an extra model to download.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for SWivid/F5-TTS and "Run a local web app for multi style and multi speaker audio"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer