DEDUPEDVoice cloning. Only clone your own voice or one you have explicit permission to use.
Who it is forA course creator who wants consistent narration without recording every lesson.
The problemRe-recording narration for every script change takes hours.
The outcomeNew narration in your own voice from text.
What you need first
- Python with pip
- A CPU is enough for the lightweight models; Kitten-TTS 2 runs realtime on CPUs and consumer GPUs per the README
Steps
- Install kittenml and load Kitten-TTS 2
- Record a clean reference clip as my_voice.wav
- Call generate with reference="my_voice.wav" and reference_text set to what you said
- Listen and adjust with the expressive preset if needed
Prompt for your agent
With KittenTTS, clone the voice in <my_voice.wav> using its transcript and narrate <script>. Verify the output sounds like the reference and contains every sentence.
Caveat. Supplying reference_text skips the Whisper pass, which is faster and avoids transcription errors.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for KittenML/KittenTTS and "Narrate content in your own cloned voice"
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