This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Free, open-source desktop audio editor: chat with an AI to load, cut, mix and render. Pure-Rust DSP on your machine, local-first, bring your own LLM key.
Hi Product Hunt, I'm Tushar, the maker of edytlab.
Why I built it: most audio edits I wanted could be said in one sentence ("match the tempos, crossfade the last 8 bars, bring it to -14 LUFS"), but doing them meant clicking through menus and remembering where every control lives. I wanted to say the edit and get it, without uploading my audio anywhere.
So edytlab is a free, open-source desktop audio editor (macOS, Windows, Linux, MIT) where you describe the edit and an AI agent runs it with 94 audio tools. The tools do the signal processing locally in Rust; the model only picks and orders them and never touches the samples. Only the chat goes to the provider you choose (Anthropic, OpenAI, OpenRouter, Groq, Gemini, your ChatGPT plan in preview, or Ollama with nothing leaving your machine). Every edit is a version you can fork, A/B compare and undo, and "plan first" lets you approve the agent's steps before anything runs.
Honest limits: no stem separation yet, the installers are unsigned (macOS and Windows warn on first launch; the release notes have the fix), and it's an offline editor, not a live DJ tool.
Feedback that would help most:
1. Which edit would you ask for first, and did it work?
2. Anything it got wrong or couldn't do (the tool list is in the docs).
3. If you run local models: which ones handle a tool list this size.
No comment highlights available yet. Please check back later!
About edytlab on Product Hunt
“Free, open-source desktop audio editor”
edytlab was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #158 on the daily leaderboard. Free, open-source desktop audio editor: chat with an AI to load, cut, mix and render. Pure-Rust DSP on your machine, local-first, bring your own LLM key.
edytlab was featured in Productivity (665.7k followers), Artificial Intelligence (483.9k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 353.3k products, making this a competitive space to launch in.
Who hunted edytlab?
edytlab was hunted by Tushar. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how edytlab stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt, I'm Tushar, the maker of edytlab.
Why I built it: most audio edits I wanted could be said in one sentence ("match the tempos, crossfade the last 8 bars, bring it to -14 LUFS"), but doing them meant clicking through menus and remembering where every control lives. I wanted to say the edit and get it, without uploading my audio anywhere.
So edytlab is a free, open-source desktop audio editor (macOS, Windows, Linux, MIT) where you describe the edit and an AI agent runs it with 94 audio tools. The tools do the signal processing locally in Rust; the model only picks and orders them and never touches the samples. Only the chat goes to the provider you choose (Anthropic, OpenAI, OpenRouter, Groq, Gemini, your ChatGPT plan in preview, or Ollama with nothing leaving your machine). Every edit is a version you can fork, A/B compare and undo, and "plan first" lets you approve the agent's steps before anything runs.
Honest limits: no stem separation yet, the installers are unsigned (macOS and Windows warn on first launch; the release notes have the fix), and it's an offline editor, not a live DJ tool.
Feedback that would help most:
1. Which edit would you ask for first, and did it work?
2. Anything it got wrong or couldn't do (the tool list is in the docs).
3. If you run local models: which ones handle a tool list this size.
Download: https://github.com/laadtushar/edytlab/releases/latest
Demo and docs: https://edytlab.com