You're looking at a specific version of this model. Jump to the model overview.
meta-innovation /ultimate_rvc:c7a02f18
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| song_input |
string
|
Audio file to convert. Upload a file directly or provide a URL (e.g. https://example.com/song.mp3). Supported formats: mp3, wav, flac, ogg, m4a, aac.
|
|
| rvc_model |
string
|
Zip archive containing your RVC voice model. Must include a .pth file and optionally a .index file.
|
|
| pitch |
integer
|
0
Min: -24 Max: 24 |
Semitone pitch shift for the converted vocals. Positive values raise pitch, negative values lower it.
|
| f0_method |
None
|
rmvpe
|
Pitch extraction method used during vocal conversion.
|
| index_rate |
number
|
0.3
Max: 1 |
Influence of the .index file on vocal conversion (0–1). Higher values make output closer to the voice model.
|
| rms_mix_rate |
number
|
1
Max: 1 |
Blending rate of the volume envelope of the converted vocals with the original (0–1).
|
| protect_rate |
number
|
0.33
Max: 0.5 |
Protection strength for consonants and breathing sounds (0–0.5). Lower values protect more.
|
| split_vocals |
boolean
|
False
|
Split audio into segments before vocal conversion.
|
| autotune_vocals |
boolean
|
False
|
Apply autotune to the converted vocals.
|
| clean_vocals |
boolean
|
False
|
Apply noise reduction to the converted vocals.
|
| room_size |
number
|
0.15
Max: 1 |
Room size of the reverb effect on converted vocals (0–1).
|
| wet_level |
number
|
0.2
Max: 1 |
Wet level of the reverb effect on converted vocals (0–1).
|
| dry_level |
number
|
0.8
Max: 1 |
Dry level of the reverb effect on converted vocals (0–1).
|
| main_gain |
integer
|
0
Min: -20 Max: 20 |
Volume gain (dB) for the converted vocal track.
|
| inst_gain |
integer
|
0
Min: -20 Max: 20 |
Volume gain (dB) for the instrumental track.
|
| backup_gain |
integer
|
0
Min: -20 Max: 20 |
Volume gain (dB) for the backup vocals track.
|
| output_format |
None
|
mp3
|
Format of the output audio file.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}