“Integrated the API into our karaoke app — job polling is straightforward and the webhook support saved us from building our own queue system.”
Alex R.
Lead developer, KaraokeFlow
Job Types
Complete reference of all Voxmin job type enums, their categories, credit costs, and payload requirements.
Job Types Reference
Karaoke Jobs (Vocal Removal Only)
Strips vocals from audio/video. No lyrics generated.
| Enum Value | Source | Output | Credits |
|---|---|---|---|
YOUTUBE_VIDEO_TO_KARAOKE_VIDEO | YouTube URL | MP4 video | 50 |
YOUTUBE_VIDEO_TO_KARAOKE_AUDIO | YouTube URL | MP3 audio | 40 |
UPLOAD_VIDEO_TO_KARAOKE_VIDEO | Uploaded video | MP4 video | 40 |
UPLOAD_AUDIO_TO_KARAOKE_AUDIO | Uploaded audio | MP3 audio | 30 |
YouTube Karaoke Payload
{
"videoId": "string (required)",
"numPasses": "number (optional, default: 2)",
"niter": "number (optional)"
}
Upload Karaoke Payload
Upload via multipart/form-data with file field.
Lyrical Jobs (Lyrics Only, No Vocal Removal)
Generates AI-powered lyric videos. No vocal removal.
| Enum Value | Source | Output | Credits |
|---|---|---|---|
YOUTUBE_VIDEO_TO_LYRICAL_VIDEO | YouTube URL | MP4 with lyrics overlay | 60 |
UPLOAD_VIDEO_TO_LYRICAL_VIDEO | Uploaded video | MP4 with lyrics overlay | 50 |
UPLOAD_AUDIO_TO_LYRICAL_VIDEO | Uploaded audio | MP4 on background | 40 |
Lyrical Payload Parameters
All lyrical job types accept these optional styling parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
enable_lyrics | bool | true | Enable AI lyric generation |
translate | bool | false | Translate lyrics to another language |
translate_to | string | "english" | Target language for translation |
use_video | bool | true | Use original video as background (YouTube only) |
background | binary | — | Custom background image (upload endpoints) |
font_name | string | "Arial" | Font family for lyrics text |
font_size | int | 50 | Font size in pixels |
base_color | string | "#ffffff" | Color of un-sung lyrics |
highlight_color | string | "#ffff00" | Color of currently singing word |
outline_size | float | 3.0 | Text outline thickness |
shadow_size | float | 1.0 | Drop shadow depth |
overlay_color | string | "#000000" | Background tint color |
overlay_opacity | float | 0.7 | Tint transparency (0–1) |
Supported Translation Languages
english, chinese, spanish, french, german, japanese, korean,
arabic, russian, portuguese, italian, hindi, vietnamese, thai,
indonesian, turkish, dutch, polish, swedish, tamil, bengali,
urdu, persian, hebrew
Translation is handled by the proprietary VoxminAI pipeline.
Karaoke + Lyrics Jobs (Vocal Removal + Lyrics)
Both strips vocals AND generates AI lyrics. Combines karaoke and lyrical processing.
| Enum Value | Source | Output | Credits |
|---|---|---|---|
YOUTUBE_VIDEO_TO_LYRICAL_KARAOKE_VIDEO | YouTube URL | MP4 with lyrics | 60 |
UPLOAD_VIDEO_TO_LYRICAL_KARAOKE_VIDEO | Uploaded video | MP4 with lyrics | 60 |
UPLOAD_AUDIO_TO_LYRICAL_KARAOKE_VIDEO | Uploaded audio | MP4 on background | 50 |
These types accept both karaoke parameters AND all lyrical styling parameters listed above.
Download Jobs (Free)
Download audio or video from YouTube without processing.
| Enum Value | Description | Credits |
|---|---|---|
YOUTUBE_VIDEO_DOWNLOAD | Download video from YouTube | 0 (free) |
YOUTUBE_AUDIO_DOWNLOAD | Download audio from YouTube | 0 (free) |
Download Payload
{
"videoId": "string (required)",
"video": "boolean (optional)",
"audio": "boolean (optional)"
}
Complete JobType Enum
enum JobType {
YOUTUBE_VIDEO_TO_KARAOKE_VIDEO = 'YOUTUBE_VIDEO_TO_KARAOKE_VIDEO',
YOUTUBE_VIDEO_TO_KARAOKE_AUDIO = 'YOUTUBE_VIDEO_TO_KARAOKE_AUDIO',
YOUTUBE_VIDEO_DOWNLOAD = 'YOUTUBE_VIDEO_DOWNLOAD',
YOUTUBE_AUDIO_DOWNLOAD = 'YOUTUBE_AUDIO_DOWNLOAD',
UPLOAD_VIDEO_TO_KARAOKE_VIDEO = 'UPLOAD_VIDEO_TO_KARAOKE_VIDEO',
UPLOAD_AUDIO_TO_KARAOKE_AUDIO = 'UPLOAD_AUDIO_TO_KARAOKE_AUDIO',
YOUTUBE_VIDEO_TO_LYRICAL_VIDEO = 'YOUTUBE_VIDEO_TO_LYRICAL_VIDEO',
UPLOAD_VIDEO_TO_LYRICAL_VIDEO = 'UPLOAD_VIDEO_TO_LYRICAL_VIDEO',
UPLOAD_AUDIO_TO_LYRICAL_VIDEO = 'UPLOAD_AUDIO_TO_LYRICAL_VIDEO',
YOUTUBE_VIDEO_TO_LYRICAL_KARAOKE_VIDEO = 'YOUTUBE_VIDEO_TO_LYRICAL_KARAOKE_VIDEO',
UPLOAD_VIDEO_TO_LYRICAL_KARAOKE_VIDEO = 'UPLOAD_VIDEO_TO_LYRICAL_KARAOKE_VIDEO',
UPLOAD_AUDIO_TO_LYRICAL_KARAOKE_VIDEO = 'UPLOAD_AUDIO_TO_LYRICAL_KARAOKE_VIDEO'
}
API Endpoints
Complete reference for all Voxmin API endpoints — jobs, downloads, pricing, and account.
MCP server overview
[object Object]
What developers say about us
From developers integrating the Voxmin API into their applications.
“Switched from manual stem separation to Voxmin API. Our developers love the predictable credit pricing and consistent output quality.”
Sarah L.
CTO, LyricVideo.io
“API rate limits are generous. We process 10,000+ jobs monthly without hitting caps. The async job model fits our architecture perfectly.”
Jennifer M.
API integration specialist, MusicTech
“The REST API is well-documented. We built a batch processor that handles 500+ tracks overnight for our venue clients.”
Marcus K.
Backend engineer, SingAlong Pro