create a task to generate audio
SN-Generate audio request parameters
Task type
create, extend, upload_extend, upload_cover, cover, use_styles_lyrics, replace_section, add_instrumental, add_vocals, gen_stem_two, gen_stem_all "create"
Model
chirp-v35, chirp-v40, chirp-v45, chirp-45+, chirp-v45-lite, chirp-v50 "chirp-v35"
Whether to make musical instruments
false
If the lyrics prompt is set, the model will create based on the prompt
Align lyrics for continuation (recommended for task=replace_dection))
Lyrics filling text (used when task=replace_dection)
Generate lyrics using GPT; Provide only brief descriptive prompts
Song style tags, comma separated strings or string arrays
Negative song style labels. Comma separated string or array
Song title
clip_id Used to continue or reference from existing audio
Continue position in seconds (extend,upload_extend)
The target range of replace_dection or add_ * task, end_2 should be>=start_2
only used for the target range of task replace_dection, infill_comtext_range. End_2 should be>=start_2
artist role configuration. Provide 'persona_id' and 'artist_clip_id' to mimic style
advanced control through sliders. All values are between 0 and 1. If omitted, use default value
voice gender
m, f