infery
← All models

Demucs

demucs

Text to Speechby Demucs

SOTA stemming model for voice, drums, bass, guitar and more.

Details

Accepts
audio

Pricing

Price
0.087 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
modelstringenum: htdemucs, htdemucs_ft, htdemucs_6s, hdemucs_mmi, mdx, mdx_extraDemucs model to use for separation
stemsSpecific stems to extract. If None, extracts all available stems. Available stems depend on model: vocals, drums, bass, other, guitar, piano (for 6s model)
shiftsintegerNumber of random shifts for equivariant stabilization. Higher values improve quality but increase processing time.
overlapnumberOverlap between segments (0.0 to 1.0). Higher values may improve quality but increase processing time.
audio_urlrequiredstringURL of the audio file to separate into stems
output_formatstringenum: wav, mp3Output audio format for the separated stems
segment_lengthLength in seconds of each segment for processing (minimum 1). Smaller values use less memory but may reduce quality. Default is model-specific.

Output

FieldTypeDescription
bassSeparated bass audio file
drumsSeparated drums audio file
otherSeparated other instruments audio file
pianoSeparated piano audio file (only available for 6s models)
guitarSeparated guitar audio file (only available for 6s models)
vocalsSeparated vocals audio file