Make sure you add your s3 details for
voice_cloning
server, so you can receive image generated in your bucket. Images generated without s3 details being added will be delete after 24 hoursFind all available voice models HERE.
Request
Make aPOST
request to below endpoint and pass the required parameters as a request body.
curl
Example
Body
json
Body Attributes
Your API Key used for request authorization.
URL (YouTube links supported) or valid
.wav
file base64 data whose audio you want to clone with the model.ID of the voice cover model Find Models Here.
Voice pitch conversion. Options:
m2f
: Male-to-Femalef2m
: Female-to-Malenone
: No pitch conversion
Pitch detection algorithm. Default: rmvpe.
Rate of control for generated voice leakage. Higher values bias model towards training data. Default: 0.5.
Seed for reproducibility. Same seed gives the same output. Pass null for a random seed.
The language of the cloned voice. Default: english.
Emotional tone of the generated voice. Default: neutral.
Floating point value for playback speed of the speaker. Default: 1.0.
Median filtering length to reduce breathiness and artifacts. Default: 3.
Mix between original loudness and fixed loudness. Default: 0.25.
Hop length for pitch changes (only applies when using mangio-crepe).
Controls similarity to original vocals (voiceless consonants). Default: 0.33.
Adjust lead vocals volume. Range: -5 (decrease) to +5 (increase).
Adjust backup vocals volume. Range: -5 (decrease) to +5 (increase).
Adjust instrumental volume. Range: -5 (decrease) to +5 (increase).
Reverb room size. Default: 0.15.
Reverb for generated vocals. Default: 0.2.
Reverb for original vocals. Default: 0.8.
High-frequency damping factor in reverb. Default: 0.7.
Whether the input sound clip is in base64 format. Default: false.
Whether you want the output to be auto-deleted from the server after a short time. Default: false.
A URL to receive a POST API call once the voice cloning process is complete.
This ID is returned in the webhook callback to identify the request.