Applio

Applio is an open source AI voice conversion suite that runs on your own computer or in the cloud. It converts any audio into another voice using ready made voice models, and the same toolkit lets users train their own voice model from a dataset by pre processing the audio, extracting features, training and exporting the result. It is released under the MIT license and is available as a standalone Desktop app or a classic Gradio web interface for Windows, macOS and Linux. The tool is aimed at music creators making AI covers, streamers and content makers who want to change their voice live, and researchers experimenting with voice models. Features include voice conversion with pitch tuning, cleanup, upscaling and batch processing, real time voice changing with low latency inference, a voice blender that merges several models into a new voice, text to speech that can be passed through a voice model, and an audio analyzer that checks a dataset before training. Users can browse community shared voice models and test them in an online playground. Applio is free. The site states there are no accounts, no paywalls and no telemetry, and everything runs locally on the user's machine. The project published a notice about changes to model access in December 2024 for responsible usage and community safety. The registry lists it under video tools, but it is an audio product.