Sound reproduction
Replicate the sound based on the uploaded audio file and generate a custom voice_id. https://platform.minimaxi.com/docs/api-reference/voice-cloning-clone The uploaded audio file format must be: mp3, m4a, wav format The…
/minimax/v1/voice_cloneBody Parametersapplication/json
Whether to add an audio rhythm identifier at the end of the audition audio
Sample audio object to enhance similarity and stability Obtained from uploading sample audio
propertiesAudio prompt / reference audio
Text prompt
The file_id of the audio to be copied is obtained through the file upload interface. Audio requirements: mp3/m4a/wav format, 10 seconds-5 minutes, <20MB
Enhanced recognition of specified languages/dialects. Can be set to auto to automatically determine, or specify a specific language
Listen to the speech models used in the audio: speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo
Whether to turn on noise reduction
Whether to enable volume normalization
Reproduce the audition text (limited to 1000 characters, support modal particles tags)
Custom sound ID (length 8-256, the first character must be a letter, numbers/letters/-/ are allowed, the last character cannot be -/)
