| What it does | AI song generator that turns ideas or lyrics into complete songs with vocals, then lets you remix, extend, split stems, and master on one canvas
| Multimodal annotation platform for skilled work
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| DE
|
|---|
| Pricing model | Freemium
| Contact for pricing
|
|---|
| Pricing | Free: 120 credits per month, no card required. Basic: $114/year (or $9.50/month), 2,500 monthly credits. Pro: $294/year (or $24.50/month), 7,500 monthly credits, includes downloadable license PDF. Ultra: $594/year (or $49.50/month), 25,000 monthly credits, includes downloadable license PDF and unlim
| Not given
|
|---|
| Key features | - Generate complete songs with AI vocals, lyrics, melody, and instrumentation in any genre
- Multiple AI models: Aether (wide styles), Reverie (lyrics sung exactly as written), Echo (structured songs), Cadence (melody-based)
- Remix, extend, and rewrite specific sections while keeping lyrics time-aligned
- Split tracks into 2, 4, or 6 stems (vocals, drums, bass, instruments)
- AI mastering on the same canvas with reference sound matching
- Train and use your own singing voice on new songs or swap onto existing tracks
- Hum a melody or upload MIDI file to build a full song around it
- Add instrumentation to a vocal or vocals to a beat
- Support for 10+ vocal languages with Reverie model
- Commercial license included on all paid plans; Pro and Ultra include downloadable license certificate
| - First-person video capture with head, helmet or chest-mounted cameras
- Dual-reviewed annotation of tasks, tools, objects and outcomes
- Privacy processing including face and text removal before release
- Documented protocols agreed before recording begins
- Contributor consent tracking and payment per accepted hour
- Provenance records with capture context, protocol version and processing history
- Evaluation, research, commercial and enterprise licence tiers
- Custom dataset collection for specified tasks and environments
- Formats: MP4 video, Parquet tables, JSON manifest
- Immutable, versioned releases for reproducible experiments
|
|---|
| What makes it different | - Can edit specific sections on the waveform without regenerating the entire song
- Available in 9 languages for global audience
- Works for producers, songwriters, content creators, and independent artists without requiring music knowledge
| - Real-world field recordings from skilled professionals instead of lab or simulated data
- Includes failure and recovery episodes with explicit outcome state labels
- Contributors are paid upfront agreed rates with transparent review decisions
- Quality assurance with sample re-annotation and written acceptance criteria
- ISO 27001 and SOC 2 Type II certification in progress
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 30 ▲ +1 (up) since last check | 3 ▲ +2 (up) since last check |
|---|
| Trust Flow (Majestic) | 15 | 0 |
|---|
| Citation Flow (Majestic) | 35 | 0 |
|---|
| Referring domains (Majestic) | 191 | 0 |
|---|
Lacuna
Curatrix