# Arpeggi Labs

**Canonical:** https://apis.io/providers/arpeggi-labs/  
**Website:** https://kits.ai  
**APIs profiled:** 5

Arpeggi Labs is the company behind Kits AI, a studio-quality AI music and audio platform for musicians, producers, and developers. Kits AI provides voice cloning and conversion, an AI singing generator with 100+ royalty-free artist voice models, vocal isolation, stem separation, AI mastering, and a voice-model blender, alongside an ethically sourced "Earn" program that pays vocalists to license digital clones of their voice. The Kits AI API exposes these capabilities as asynchronous inference jobs over a REST interface at arpeggi.io/api/kits/v1, authenticated with a bearer API key: create a voice conversion, vocal separation, stem split, or voice-blend job, then poll for the signed output file URLs. Arpeggi Labs is an a16z portfolio company; its earlier product was Arpeggi Studio, a web3 in-browser music creation platform.

## Kin Score — 48.4 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 48.4).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 57.8 |
| Governance | 16.7 |
| Contract Governance | 16.7 |
| Operational Transparency | 23.7 |
| Developer Ergonomics | 58.9 |
| Commercial Clarity | 44.7 |
| Access Clarity | 44.7 |

## Agent readiness — 31.4 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | documented |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (5)

- **Arpeggi Labs Stem Splitter API** — Split an audio track into vocal and instrument stems.
- **Arpeggi Labs Vocal Separation API** — Isolate vocals from a mixed audio track.
- **Arpeggi Labs Voice Blender API** — Blend two to four voice models into a new voice model.
- **Arpeggi Labs Voice Conversion API** — Convert an input performance to a target voice model.
- **Arpeggi Labs Voice Models API** — Browse and retrieve available voice models.

## MCP servers (1)

- **Arpeggi Labs MCP Server** — Candidate MCP server for the Kits AI API. No official hosted/remote MCP server was found published by Arpeggi Labs at enrichment time; this is a derived candidate tool list, one...

## Security (2)

- **Arpeggi Labs Authentication** — http · 1 scheme
- **Arpeggi Labs Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Company, Music, Audio, Artificial Intelligence, Voice, Machine-Learning, Generative AI, Media

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/arpeggi-labs/). Scores are computed from the provider's own public artifacts under a published rubric.