Skip to content

Releases: barongartner/FreeVoice

Release list

FreeVoice Studio 1.0.0

FreeVoice Studio 1.0.0 Latest
Latest

Choose a tag to compare

View all tags
@barongartner barongartner released this 06 Jul 00:49
v1.0.0
c09b81a

Every tier of AI text-to-speech in one native Windows app. Fully local, free forever.

Setup:

  1. Install Python 3.12 (check 'Add to PATH') and run: pip install -r https://raw.githubusercontent.com/The-Berin/FreeVoice/main/requirements.txt
  2. Run FreeVoice-Studio-Setup-1.0.0.exe (no admin needed) - or unzip the portable build.
  3. Launch. Models download automatically on first use of each engine.

What's inside:

  • Tier 3: Chatterbox - beat ElevenLabs 65%-24% in blind listening tests, voice cloning + emotion control
  • Tier 3: F5-TTS - research-grade voice cloning (non-commercial license)
  • Tier 2: Kokoro - near-instant drafts, 50+ preset voices
  • Voice cloning from 7-20s of audio, multi-voice [Speaker] scripts, job queue with progress/ETA
  • Effects (Deep Voice, Radio, Echo, Robotic), denoise + loudness normalize, MP3/WAV
  • Native C# app supervising a local Python engine server; REST API at 127.0.0.1:7899 for pipelines

Docs: https://github.com/The-Berin/FreeVoice/tree/main/docs

Assets 4
Loading