Who it is forA creator localizing videos or courses.
The problemSeparate TTS vendors per language get expensive and inconsistent.
The outcomeWAV files in each target language, optionally in one consistent voice.
What you need first
- Python 3.11 (developed and tested on Debian 11)
- A CUDA GPU for Turbo and Multilingual; Nano also runs on CPU
- A short reference audio clip if you want to clone a voice
Steps
- Install with
pip install chatterbox-tts - Load ChatterboxMultilingualTTS.from_pretrained with t3_model set to v3
- Call generate with your text and language_id such as fr or zh
- Make sure any reference clip matches the language tag to avoid accent transfer
Prompt for your agent
With resemble-ai/chatterbox, load ChatterboxMultilingualTTS with t3_model="v3" and generate <my paragraph> in French, Spanish and Hindi using language_id, saving each as a WAV.
Caveat. The Single Language Pack has dedicated finetunes for some languages if you need tighter quality.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for resemble-ai/chatterbox and "Narrate the same text in many languages"
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