Voice clone for recurring episodes
Keep the next episode in the same voice
Voice Clone Series Studio makes a voice clone of your own voice from a clean single-speaker sample of 10 to 300 seconds and keeps it as a named, reusable voice. Each new script then becomes MP3 narration in that voice, for every episode of a podcast, course, or creator series. Voice Clone Series Studio works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Voice Clone Series Studio and tell me when I need to sign in: https://beatra.ai/skills/voice-clone-series-studio/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.GitHub ↗Docs ↗
One voice that carries the whole series
Clone the voice once
Create a reusable personal or brand voice from a clean single-speaker sample.
Write the next episode
Drop in each new script and hear it in the same custom AI voice.
Stay consistent
Keep podcasts, lessons, and recurring updates sounding like the same host.
How it is made
Create the series voice from speech you own
Use a clear single-speaker sample to make a named reusable voice the later episodes can keep choosing.
Use one clear speaker · Give the voice a name you recognize · Hear it on a short first reading
Treat each script as the next episode
Keep episode order, titles, and recurring pronunciations together so the series stays easy to follow.
Keep episode titles in order · Reuse the same named voice · Carry names and terms across episodes
Turn the new script into the next voiceover
Read the new episode in the cloned voice, then keep going as the series grows.
Drop in the next script · Hear the episode in the same voice · Keep later episodes on the same host
Podcasts, courses, and creator updates
Podcast voice clone
Record the next episode voiceover in the host voice listeners already know.
Course and lesson updates
Add a new lesson or weekly note without recasting the teacher.
Creator and brand series
Keep channel updates and brand messages in one recognizable voice.
Inputs and outputs
Input · Audio — A clean single-speaker recording of the voice to clone
- Formats
- MP3, WAV
- Specifications
- 10–300 s; up to 20 MB each
Input · Text — The first or next episode script
Output · Audio — Each new episode narrated in the same named voice
- Formats
- MP3
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Audio — A clean single-speaker recording of the voice to clone | MP3, WAV | 10–300 s; up to 20 MB each |
| Input | Text — The first or next episode script | — | — |
| Output | Audio — Each new episode narrated in the same named voice | MP3 | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What do I need to start?
A clean sample of your own voice and the first episode script. Later episodes only need the next script.
Can later episodes keep the same voice?
Yes. Each new script becomes the next episode, update, or lesson in the saved voice.
What kinds of series is this for?
Podcasts, course updates, creator episodes, and recurring brand messages that should sound like the same host.
Related Skills
