NNiceVois
Voice conversion

AI voice changer online

Change the voice in a vocal or song. Use a licensed library voice, a voice you've trained, or your own RVC model.

No voice yet? Train your own voice

Voice training

Train your own voice

One free training per signed-in account. Up to 5 minutes of audio and 150 epochs.

A few minutes of clean, varied singing can be enough for a good, usable voice model. Start with your own voice or a voice you have permission to use.

Add up to 50 WAV, MP3, FLAC, M4A, or OGG files. NiceVois keeps them separate and prepares them together as one private training dataset.

.pth

This name is used for the .pth, .index, and complete ZIP package.

Standard is selected automatically.
200 epochs

Recommended: add your audio and NiceVois will suggest the right number.

Clean audio produces a better model. Use a dry voice recording with minimal music, echo, or background noise. Prepare your audio first if it needs it.

Voice conversion

Convert a vocal or full song with your voice

Loading allowance...
Five free conversion download minutes. Listening is free, only downloading uses minutes.

Convert a vocal or a full song with a saved NiceVois voice or your own RVC model. Every conversion includes the normal RVC output and a NiceVois Clean Consonants version for more natural sibilance and breaths. Hear standard RVC versus NiceVois.

Voice modelChoose a saved voice or bring your own
.pth or model .zip
Your NiceVois voices
Or drop your RVC model here

Only upload a model you own or have permission to use. By uploading, you agree to the Acceptable Use Policy.

Pitch shift
Output Conversion results

Your converted audio will appear here

Choose a voice and audio on the left, then press Convert.

No model yet? Use a library voice.

Open Choose a voice above and switch to NiceVois voice library. You can use a licensed voice without training or uploading a model. Check its credit and conditions before publishing.

Your account includes five free voice-conversion download minutes. Listening is free. Need more? See the subscription. Voice conversion has its own allowance, separate from the free audio tools.

Hear it first

An original vocal. A library voice.

The same words, melody and timing, converted with AI Minagi and NiceVois Clean Consonants.

Original

The recorded vocal

Converted

AI Minagi

Voice credit: AIみな〜ぎ(CV 花夜みなぎ). Loudness-matched excerpts from an authorized source recording. This is a library-voice listening example, not a guaranteed result or a free-training benchmark.

About this voice →

How to change the voice in a song online

  1. Choose a voice

    Open Choose a voice. Select one of Your voices, or switch to NiceVois voice library to use a licensed voice. You can also upload your own RVC .pth or model ZIP.

  2. Add your audio

    Drop in an isolated vocal or a full song. For a song with instruments, select Separate the stems first. Set the pitch and output format if needed.

  3. Convert and listen

    Press Convert, listen to the result and download the version you prefer. A vocal conversion includes normal RVC and NiceVois Clean Consonants outputs; a full-song conversion also returns the mix and its parts.

Use recordings and voices you have permission to use. A licensed voice does not license the song. Voice library terms · Acceptable use.

Common questions

What is an AI voice changer?

An AI voice changer converts a recorded voice with a different voice model while following the original words, melody and timing. NiceVois uses RVC voice-to-voice conversion for singing and speech; it does not generate a song or read typed text.

Can I use it without training a voice?

Yes. Open Choose a voice and switch to NiceVois voice library. These voices are used with their creators' permission. Each voice has its own credit and conditions; commercial use is allowed only where that voice explicitly permits it. Library model files cannot be downloaded.

Is the voice changer free?

Your account includes five free voice-conversion download minutes, and listening is free. Conversion downloads use a separate allowance from the free separators. Additional downloads have paid options; an active Unlimited subscription includes unlimited conversion under the fair-use terms.

Can I change the singer in a full song?

Yes. Select Separate the stems first before converting a full song. NiceVois separates the lead vocal, backing vocals and instrumental, converts the lead, then returns a mixed cover and the separated parts. The original instrumental and backing vocals stay in the mix.

Is this a real-time voice changer for calls or games?

No. NiceVois changes uploaded audio files. It does not change your live microphone in Discord, calls or games. Upload your recorded singing or speech, convert it and download the result.

How is voice changing different from voice cloning?

Voice cloning trains a reusable voice model from permitted recordings. Voice changing applies an existing model to another recorded performance. If you want to create your own voice model first, use the AI voice cloning for singing page.

Persistent cloud storage

Your model library

Your voice models are files you own. Download them once and no platform can take them away.

Loading…
Paid model packages stay saved until you delete them.

Your .pth, .index, ZIP, and private listening preview remain available after closing the browser or restarting your computer. A model from the free training run is kept for 7 days and shows its expiry date; download it before then. Full-resolution source audio and temporary training files are removed after validation.

⌁Loading your models

Checking private cloud storage…