Clones and designs voices, dubs videos, dictates and transcribes audio fully on your machine, with a local API and MCP server for AI agents.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with VoiceStudio connected:
- Generate Speech
Use VoiceStudio to turn text into speech in a chosen voice profile: ‹what you need›
- Clone a Voice
Use VoiceStudio to create a reusable voice profile from a clean reference recording: ‹what you need›
- Design a Voice
Use VoiceStudio to create a new voice: ‹what you need›
Connect it over MCP
Connect VoiceStudio as an MCP server, following its setup instructions at https://github.com/debpalash/VoiceStudio#get-started
Setup guide: github.com/debpalash/VoiceStudio
Install the CLI
curl -fsSL https://voicestudio.sh/install | sh
Setup guide: github.com/debpalash/VoiceStudio
Call the API
Auth None needed
Setup guide: github.com/debpalash/VoiceStudio
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCPAPICLI
- Auth
- None
- Skills
- 5
Skills
Generate Speech
Turns text into speech in a chosen voice profile, returning WAV or Ogg/Opus audio inline or as a file.
Clone a Voice
Creates a reusable voice profile from a clean reference recording for later speech generation.
Design a Voice
Creates a new voice from a text description of gender, age, pitch, style and accent, then saves it as a profile.
Transcribe Audio
Transcribes audio to text locally in 646 languages, from base64 input or a file under the configured base path.
Dub Videos
Translates and dubs videos with speech timed to the original, including multi-speaker dubbing and export.