Open-source AI model for audio noise removal
Inworld Voice Isolator is an open-source AI model that removes background noise, music, and other voices from audio recordings in real time at 48 kHz while preserving the original voice and breathing.
Open-source AI model for audio noise removal
A powerful open-source model for cleaning speech from noise has been released — Inworld Voice Isolator.
What the model does
- Removes background conversations, music, and noise
- Preserves voice and even breathing from the original recording
- Works in real time at 48 kHz
- Splits audio into voice and everything else — music, noise, echo, and other voices
Training
The model was trained on 10,000 hours of speech.
Link
Why it matters
AnalysisInworld Voice Isolator provides developers and producers with a free professional audio cleaning tool, which is critical for podcasts, video content, and AI assistants.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
JSON — Structured Data for Programs, APIs, and AI Agents
A complete hands-on guide to JSON: syntax specifications, serialization via parse and stringify, REST API consumption, JSON Schema validation, and structured outputs for LLMs.
DOCX and XLSX Formats: When AI Needs to Deliver Production-Ready Documents
A comprehensive hands-on guide to generating and processing DOCX documents and XLSX workbooks with AI: comparing against Markdown and CSV, prompt engineering, formula design, and code automation.
How to really use AI agents
A concise practical note on using AI agents deliberately and effectively.
Matt's practical approach to reviewing a 21,000-line PR
Matt demonstrates a 70-minute workflow for reviewing a 21,000-line PR: splitting it into smaller PRs, manual review, architectural focus, and retro analysis.