cinemasetfree.com
pseudoram/rvc-v2
Speech to speech with any RVC v2 trained AI voice
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
crepe_hop_length | integer | When `f0_method` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds. | 128 | — |
custom_rvc_model_download_url | string | URL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc_model' value. | — | — |
f0_method | string | Pitch detection algorithm. 'rmvpe' for clarity in vocals, 'mangio-crepe' for smoother vocals. | "rmvpe" | rmvpemangio-crepe |
filter_radius | integer | If >=3: apply median filtering to the harvested pitch results. | 3 | min: 0, max: 7 |
index_rate | number | Control how much of the AI's accent to leave in the vocals. | 0.5 | min: 0, max: 1 |
input_audio | string(uri) | Upload your audio file here. | — | — |
output_format | string | wav for best quality and large file size, mp3 for decent quality and small file size. | "mp3" | mp3wav |
pitch_change | number | Adjust pitch of AI vocals in semitones. Use positive values to increase pitch, negative to decrease. | 0 | — |
protect | number | Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable. | 0.33 | min: 0, max: 0.5 |
rms_mix_rate | number | Control how much to use the original vocal's loudness (0) or a fixed loudness (1). | 0.25 | min: 0, max: 1 |
rvc_model | string | RVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom_rvc_model_download_url' is provided, this will be automatically set to the name of the downloaded model. | "Obama" | ObamaTrumpSandyRoganCUSTOM |
crepe_hop_lengthintegerWhen `f0_method` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds.
128custom_rvc_model_download_urlstringURL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc_model' value.
f0_methodstringPitch detection algorithm. 'rmvpe' for clarity in vocals, 'mangio-crepe' for smoother vocals.
"rmvpe"filter_radiusintegerIf >=3: apply median filtering to the harvested pitch results.
3min: 0, max: 7index_ratenumberControl how much of the AI's accent to leave in the vocals.
0.5min: 0, max: 1input_audiostringUpload your audio file here.
output_formatstringwav for best quality and large file size, mp3 for decent quality and small file size.
"mp3"pitch_changenumberAdjust pitch of AI vocals in semitones. Use positive values to increase pitch, negative to decrease.
0protectnumberControl how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable.
0.33min: 0, max: 0.5rms_mix_ratenumberControl how much to use the original vocal's loudness (0) or a fixed loudness (1).
0.25min: 0, max: 1rvc_modelstringRVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom_rvc_model_download_url' is provided, this will be automatically set to the name of the downloaded model.
"Obama"d18e2e0a6a6dUpdated: 7/25/20261.5M runs