Train a new vocal changer model

Prepare your datasets

Clean dry samples

High-quality voice changer models require clean and dry vocal/instrument samples:

• Without any reverb, delay, chorus effects
• Without background noise
• Without instrumentals
• Without any harmonies or doubles (Monophonic for instruments)

30-100mins of samples are recommended for a good quality model.

• For a voice model, you can use samples of speech and singing vocals.
• For an instrument model, you need to record monophonic tracks.

Room reverberations

Samples recorded with big room reverb might cause error recognitions and result in unexpected model performances.

Samples from stem splitter

When you are using stem splitter, the output quality might be damaged too low for training. For a higher quality voice model, please optionally use vocals from stem splitter.

Record samples

1. Quality microphone with audio interface

Professional microphones with audio interfaces bring high-quality recordings. You'll need recording software to connect to your interface, record, edit, and mix your samples.

When recording for a model, avoid microphones that are not built for recording:

1. Phone or laptop mics
2. Lapel or headset mics
3. Karaoke mics
4. Earphone mics or bluetooth earphones like air pods (these are usually for phone talks)
2. Recording environment

Unwanted background noises can include people talking, electrical hums and buzzes, traffic and outdoor noise, as well as movements of accessories or objects. To prevent these noises from interfering with your recording, it is important to select a quiet location. Choose a place where you can minimize or eliminate unexpected noise disturbances.

Sound reflections can occur due to the presence of hard, level surfaces, resulting in reverberation or echoes in your recordings. This can give your tracks a hollow or distant quality, detracting from the desired intimacy and clarity.

Try clapping your hands sharply in the room and listen carefully. If you perceive a fluttering sound or a prolonged echo, it indicates the presence of reverb issues.

To address this, incorporate soft materials that can absorb sound. Consider using carpets, rugs, or thick curtains to significantly reduce reflections. Covering hard floors and, if possible, hanging curtains over windows, as well as placing furniture with fabric coverings in the room, can be beneficial.

Avoid using hard surfaces as they contribute to the problem. If you cannot afford professional acoustic panels, you can utilize everyday items such as canvas paintings, tapestries, or foam tiles to break up these surfaces.

When setting up your microphone, be mindful of its placement. Avoid positioning it too close to walls or in corners. Instead, aim for the center of the room or experiment with different locations to find the optimal spot with minimal reverb.

3. Headphone bleed

During recordings, particularly when capturing vocals, it is common for the audio from headphones to bleed into the microphone. This issue arises when the volume of the headphones is set too high or when open-back headphones are being used. This might be acceptable when recording for a song, but try to avoid this bleeding when recording for your voice model.

4. Microphone placement

For regular volume, it is recommended to position yourself about 2 inches away from the microphone. However, for louder phrases or when belting, it is advisable to increase the distance to around 4-6 inches. It is important to note that you should always stay closer than 12 inches from the microphone to maintain optimal audio capture.

Creating Space for Belting

When engaging in belting techniques, it's important to allow yourself ample space, both in terms of microphone distance and the size of the room you're in. Excessive sound isolation, such as being confined in a closet or booth, or surrounding your microphone with foam, can easily result in overloading the microphone capsule. If you're unsure, it's advisable to incorporate more room sound when performing belted phrases.

Languages

For a voice changer model, you don’t need to keep all samples in one language.

Singing or speech

For a voice changer model, there is no big difference between speech samples and singing samples. But for a singing voice changer model, it is more suitable to use singing samples for training.

File quality settings

The audio quality of your samples directly impacts the quality of your voice model.

We recommend you to set your audio quality in:

• Bit Depth = 16-bit
• Sample Rate = 44.1khz or 48khz
• Lossless file format (.wav or .flac)

Post-processing

To maintain the natural character and clarity of your target voice:

• No overlaps: multi-layered vocals can complicate AI's analysis. Place the overlapped takes at back and stick to a single vocal track to ensure the AI can accurately process and learn from your samples.
• No hard cuts: hard cuts can create abrupt starts or ends, which are not normal in a natural singing sound and can introduce clicks or pops. Use smooth fades at the beginning and end of the vocal clip for a more natural transition.
• No duplicating sections: Duplicated sections don't help for the training. Your voice model benefits from the natural variation of performance.
• Control the volume: Make sure your samples stay around 30-50% of your meter. Use a volume rider or automation to make sure volume levels are consistent across your entire dataset. The aim is to create a consistent volume level across the recording while keeping the dynamics within sections.

Train your voice changer model

Custom slots

You can customize one voice changer model in one slot.

Click on a slot to start uploading your samples.

After all samples being uploaded, the training will start automatically. You can check its status by refreshing the webpage.

When the page jumps back to the slot list with a new trained model, you’re all set.

Click ‘Open in ACE’ to open ACE Studio and use your new trained model.