Stems
For Music
Name | Stem Name | Description |
---|---|---|
Instrumental | instrumental | Music without vocals, only instruments |
Drums | drums | Percussion instruments producing rhythmic beats |
Vocals | vocals | Isolates singing and vocal sounds |
Bass | bass | Instruments producing low-frequency sounds, typically the bass guitar or synthesizer bass lines |
Other | other | Remaining instrumentation after removing vocals, drums, and bass |
Guitar | guitar | Instruments from the guitar family, including electric, acoustic, and classical guitars |
Other-x-Guitar | other-x-guitar | Remaining instrumentation after removing vocals, drums, bass, and guitar |
Piano | piano | Instruments like Rhodes piano, upright piano, grand piano, and keyboard |
Wind | wind | Instruments like flute, saxophone, producing sound by vibrating air |
For Dubbing/Film and Captioning/Transcription
Name | Stem Name | Description |
---|---|---|
Music | music | General music audio, including instruments and melodies |
Dialogue | dialogue | Spoken conversation or interaction between characters |
Transcription | transcription | Text representation of spoken words or audio content |
Alignment | alignment | Synchronization of audio and corresponding text or captions |
Music removal | music_removal | Removing music from audio while maintaining synchronization |
Background (Music & FX) | music_fx | Background audio and sound effects synchronized with text or captions |
Example
In the provided cURL command, the "name" field in the JSON payload specifies the desired stem type for processing the audio file. It allows you to indicate what specific part of the audio you want to extract or process.
curl -L -X POST 'https://groovy.audioshake.ai/job/' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <TOKEN>' \
--data-raw '{
"metadata": {
"format": "wav",
"name": "vocals"
},
"callbackUrl": "https://example.com/webhook/vocals",
"assetId": "abc123"
}'