Voicebox

What is Voicebox?

Voicebox is a Voice Cloning tool. Open-source AI voice studio for cloning, dictating, and creating. Voicebox is free to use. It is available on Windows, macOS and Linux. It is aimed at developers, content creators and researchers.

Open-source AI voice studio that enables voice cloning, speech generation with multiple TTS engines, and transcription. It supports 23 languages and includes a local LLM for text refinement. Runs on macOS, Windows, Linux, and Docker with GPU acceleration.

Built for developers, content creators and researchers.

Key capabilities

• Voice Cloning
• Speech Generation
• Transcription
• Agents

Features

• Multi-Engine Voice Cloning

• Emotions & Paralinguistic Tags

• Post-Processing Effects

• Unlimited Generation Length

• Generation Versions

• Async Generation Queue

• Voice Profile Management

• Global Dictation & Voice Input

• Speech-to-Text

• Captures

• Agent Voice Output

• Voice Personalities

Use cases

• Clone voices for personalized audio content creation
• Generate speech in 23 languages for international audiences
• Transcribe audio using Whisper-based dictation
• Refine text with a local LLM for better output quality
• Run agents like Claude Code with cloned voice output

Pros & cons

Pricing

Free.

AI models

• Qwen 1
• ElevenLabs

Developer & API

Security & compliance

• Encryption
• Data deletion

As stated on Voicebox's website — not independently verified by AiByts.

FAQ