Loading...
Loading...
Alibaba Cloud’s Qwen team has open-sourced Qwen3-TTS, a new text-to-speech model family aimed at practical production use with stable, expressive output, low-latency streaming, and features like free-form voice design and vivid voice cloning. The release is quickly spawning an ecosystem: projects like Voicebox package Qwen3-TTS into a polished, browser-based “voice synthesis studio,” while other community apps focus specifically on voice cloning workflows. Together, the updates signal a broader trend toward accessible, end-to-end open-source voice generation stacks—models plus tooling—making advanced TTS and cloning easier to experiment with and deploy.
Rowboat Labs has released “Rowboat,” an open-source “AI coworker” project that emphasizes built-in memory, according to its GitHub repository. The project is written in TypeScript and, at the time of the listing, shows 79 GitHub stars and 4 forks. The repository credits contributors including ramnique, JollyRogerz, and username1290. While the available description is brief and does not detail specific features, deployment options, or supported models, the positioning suggests a tool aimed at assisting users with ongoing work by retaining context over time. The project’s open-source nature may make it easier for developers to inspect, modify, and integrate the coworker concept into their own workflows, but further technical specifics are not provided in the supplied content.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning. Language: Python Stars: 29 Forks: 2 Contributors:
The open-source voice synthesis studio powered by Qwen3-TTS. Language: TypeScript Stars: 392 Forks: 40 Contributors: glaucusj-sai,chazmofdoom,rifatwebdev,jannone,hopehubris
Open-source voice cloning app using Qwen3-TTS