Applio

Applio converts recordings and microphone input into another voice for musicians making AI covers, streamers and speech creators. You can choose community voice models or train a model from your own recordings.

• Audio conversion: Convert songs or speech into another voice, adjust pitch, clean and upscale audio, and process multiple files in batches.
• Live voice changes: Change your voice during singing, streams and calls with low-latency processing.
• Custom voice models: Prepare your audio dataset, check its quality with the audio analyzer, then train and export a voice model.
• Voice blending: Combine voice models and control how much each contributes to the resulting voice.
• Text-to-speech: Generate spoken audio from text and pass it through a voice model.

Applio is free and open source under the MIT license. It runs on Windows, macOS and Linux through a standalone desktop app or a Gradio browser interface. Local audio processing and model training run on your machine, require no account and collect no telemetry. The playground and Google Colab provide cloud alternatives. Plugins support further customization.