An open alternative to ElevenLabs and OpenAI Whisper for complex audio tasks. It integrates LLMs with specialized foundation models to generate speech, music, and talking heads.
Tech Stack
PythonAI, ML & Data
Why AudioGPT?
• Multimodal capabilities
• State-of-the-art models
• Extensible architecture
Limitations
• Extreme VRAM usage
• Complex installation
• Experimental status
3/5/2026
Last Update
866
Forks
54
Issues
Other
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to AudioGPT instantly boosts your runway.
