Voicebox is a desktop app for voice cloning and speech synthesis. Feed it a few seconds of audio and it clones the voice using models like Qwen3-TTS. Then you arrange the generated speech on a timeline — drag clips around, layer different voices, edit the output like you would in a DAW. Includes Whisper for transcription so you can edit based on the actual text. Runs locally. No cloud processing, no subscription. https://github.com/jamiepine/voicebox #github #opensource

Summary

VoiceBox is a desktop app for voice cloning and speech synthesis. It allows users to edit and arrange generated speech locally without subscriptions or cloud processing.

Key Points

1. VoiceBox clones voices from a few seconds of audio input.
2. It uses models like Qwen3-TTS for voice synthesis.
3. Users can arrange speech on a timeline like in a DAW.
4. The app allows layering of different voices and editing.
5. Whisper integration provides transcription for text editing.
6. VoiceBox operates locally without cloud processing.
7. There are no subscription fees for using the app.

Tags

Repurpose Ideas

• Blog post: How to use VoiceBox for audio projects
• Video tutorial: Voice cloning with VoiceBox
• Social media post: Benefits of local voice synthesis apps