Applio
Free, open-source voice conversion suite for training voice models, converting audio and changing your voice live.
Applio is a free, open-source AI voice conversion suite. Applio converts recorded audio or live microphone input into another voice, trains custom voice models from your own datasets, blends models and adds text-to-speech. It is used by downloading the Desktop app or the Gradio WebUI for Windows, macOS or Linux, then choosing or training a voice model.
Best for Hobbyists and audio creators who want a no-cost, locally run tool for voice conversion and model training.
- Platforms
- Windows, macOS, Linux
- Pricing model
- Free
- Free plan
- Yes
- Made by
- IAHispano
- Added
Last verified: . Information taken from applio.org.
What is Applio?
Applio is an open-source suite for AI voice conversion released under the MIT license. It takes an audio file, or live microphone input, and re-renders it in a different voice using a voice model. Users can pick a model shared by the community or train one from their own recordings; the training workflow covers pre-processing, feature extraction, training and export. Further tools blend several models into a new voice, generate speech from text and pass it through a model, and analyse a dataset before training starts. Applio is available as a standalone Desktop app and as a Gradio WebUI, for Windows, macOS and Linux, and can also be run in the cloud. The project is maintained by IAHispano and a volunteer community, needs no account, and sends no telemetry.
Key Features
Voice Conversion
Re-voices an audio file with a chosen model, with controls for pitch, clean-up and upscaling and the option to process files in batches.
Real-Time Voice
Converts microphone input live at low latency for use while singing, streaming or on a call.
Model Training
Builds a custom voice model from your own dataset through pre-processing, extraction, training and export stages.
Voice Blender
Merges two or more voice models into a new one and lets you set how much each source contributes.
Text-to-Speech
Turns written text into speech and then routes that speech through one of your voice models.
Audio Analyzer
Reports on the condition of a dataset so you can judge whether it is ready before you train on it.
How Applio works
Get Applio
Download the standalone Desktop app, or use the classic Gradio WebUI instead.
Choose or train a voice
Select a voice model shared by the community, or train one on your own audio dataset.
Convert your audio
Run a song, a speech recording or microphone input through the model.
Use Cases
- Making an AI Cover
- Convert the vocal of a song into another voice using a ready-made model.
- Changing Your Voice on Stream
- Apply a voice model to your microphone in real time during a broadcast or call.
- Training a Custom Voice
- Create a model from your own recordings and export it for later use.
- Narration from Text
- Generate spoken audio from a script and render it in a specific voice model.
- Checking a Dataset
- Inspect recordings with the analyzer before committing time to training.
Things to know
- MIT license
- The code is MIT-licensed and may be used, changed and redistributed for personal, research or commercial projects.
- Runs locally
- The site states that no account is needed, no telemetry is collected and everything runs on your own machine.
- Model access rules changed
- A December 2024 announcement describes changes to model access made for responsible use and community safety; the site also publishes Terms of Use.
FAQs
What is Applio?
Applio is a free, open-source AI voice conversion suite for converting audio, training voice models and changing a voice in real time.
Is Applio free?
Yes. Applio is MIT-licensed and free to use, modify and redistribute, including for commercial work, with no paywall.
Which operating systems does Applio support?
Applio runs on Windows, macOS and Linux, and the site says it can also be used in the cloud.
Do I need an account to use Applio?
No. Applio requires no account and collects no telemetry; processing happens locally on your machine.
Can I train my own voice model in Applio?
Yes. Applio includes a training workflow that prepares your dataset, extracts features, trains the model and exports it.
Who makes Applio?
Applio is an independent community project credited to IAHispano and developed openly on GitHub.
Does Applio have text-to-speech?
Yes. Applio can generate speech from text and then run it through a voice model.
Who it's for
- Music hobbyists
- Streamers
- Audio engineers
- Content creators
- Open-source contributors
Comments
No comments yet. If you have used Applio, tell other readers how it went.
Alternatives to Applio
| Tool | Free plan | Starting price | API |
|---|---|---|---|
 ElevenLabsAI audio platform for text to speech, voice cloning, transcription, dubbing, music and conversational voice agents. |
Yes | — | Yes |
 Fish AudioAI voice platform for text to speech and voice cloning with emotion tags, a large voice library and a developer API. |
Yes | — | Yes |
 Inworld AIRealtime voice AI platform offering text-to-speech, speech-to-text, a speech-to-speech API and LLM routing. |
Yes | — | Yes |
 LazybirdAI voiceover generator that turns scripts into downloadable speech with 200+ voices, voice cloning and an API. |
Yes | — | Yes |
 ListnrAI voice generator for text to speech, voice cloning and narration in a browser-based studio. |
Yes | — | Yes |
Listed in the same categories as Applio. A starting price appears only where we checked it on the maker’s pricing page; a dash means not checked or not published. All Voice Cloning & Voice Changer tools