Official vendor OpenAPI document · agent-readyMediaVideo Processingbearer, oauth234 EndpointsREST
For Agents
Upload songs, quote and render lyric videos or Spotify Canvas loops, and track, cancel, or retry each video job on Kinetune.
Use for: I want to make a lyric video for my new single, Quote how many credits a Spotify Canvas will cost, Upload a song and check its analysis, List all videos rendered for a song
Not supported: Does not distribute music to streaming services, collect royalties, or edit arbitrary video timelines. Use for generating lyric videos and Spotify Canvas loops from your own songs only.
The Kinetune API turns your uploaded songs into lyric videos and Spotify Canvas loops, from quoting the credit cost to rendering and retrying the finished video. You upload audio, organise songs under artists with their photos, read each song's analysis, and pick or publish reusable Looks that set the visual style. Video jobs can be cancelled, retried, or delivered to a signed callback URL when they finish, and a stock media search supplies backgrounds.
Install Jentic One Beta
Connect the Kinetune API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Kinetune API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fkinetune.com%2Fkinetune" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fkinetune.com%2Fkinetune" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Kinetune API.
Quote the credit cost of a lyric video or Canvas before rendering it with POST /api/v1/quotes
Render a lyric video or Spotify Canvas loop for a song, with up to 4 variations and an optional callback_url
Upload songs, rename or archive them, and read or rerun each song's analysis
Organise artists with their photos and set the artist picture used in videos
Browse, rename, delete, and publish or unpublish Looks that define a video's visual style
Search stock photos and videos for backgrounds, or upload your own background file
Cancel a rendering video, make it again, or delete it once it is no longer needed
Use Cases
Patterns agents use Kinetune API for, with concrete tasks.
★ AI agent release assistant through Jentic
A musician's agent prepares visuals for a release without the musician touching the Kinetune dashboard. Through Jentic the agent searches for 'make a lyric video', loads the Kinetune quote and create operations with their input schemas, quotes the cost, then submits the render with the same song_id and options. The Kinetune key is attached by your own Jentic One instance at call time, so the agent never holds it.
Quote a lyric video for song_id 'sng_123' with POST /api/v1/quotes, then create it with POST /api/v1/videos using the same options and poll GET /api/v1/videos/{video_id} until it is ready
Spotify Canvas loops for a back list
A label refreshing the Spotify Canvas loops on a back list of releases lists the songs for an artist, quotes a Canvas for each, and creates the loops in turn. Each video can carry your own metadata, such as an order id, and a callback_url so the finished file is posted to your system instead of being polled.
List songs with GET /api/v1/songs filtered by artist_id, then for each song quote and create a Canvas with POST /api/v1/quotes and POST /api/v1/videos, passing a callback_url
Song library and artist setup
Before any video is made, the songs and artists need to be in place. Kinetune lets you create an artist, add photos and set the artist picture, upload a song's audio and cover art, and read the song analysis that drives lyric timing. If the analysis looks wrong, you can request a fresh analysis for that song.
Create an artist with POST /api/v1/artists, upload a song with POST /api/v1/songs, then read GET /api/v1/songs/{song_id}/analysis and rerun it with POST /api/v1/songs/{song_id}/analysis if needed
Video job recovery
Rendering jobs sometimes need intervention. An agent can list videos for a song, read each video's state, cancel a job that was started with the wrong options, make a failed video again, or delete videos that are no longer needed, keeping the library tidy.
List videos with GET /api/v1/videos for a song_id, then call POST /api/v1/videos/{video_id}/retry on any video that failed
Key Endpoints
34 endpoints — the kinetune api turns your uploaded songs into lyric videos and spotify canvas loops, from quoting the credit cost to rendering and retrying the finished video.
METHOD
PATH
DESCRIPTION
POST
/api/v1/quotes
Quote a lyric video or Canvas
POST
/api/v1/videos
Create a lyric video or Canvas
GET
/api/v1/videos/{video_id}
Get a video
POST
/api/v1/videos/{video_id}/retry
Make a video again
POST
/api/v1/songs
Upload a song
GET
/api/v1/songs/{song_id}/analysis
Get a song's analysis
GET
/api/v1/looks
List Looks
GET
/api/v1/stock
Search stock media
POST
/api/v1/quotes
Quote a lyric video or Canvas
POST
/api/v1/videos
Create a lyric video or Canvas
GET
/api/v1/videos/{video_id}
Get a video
POST
/api/v1/videos/{video_id}/retry
Make a video again
POST
/api/v1/songs
Upload a song
GET
/api/v1/songs/{song_id}/analysis
Get a song's analysis
GET
/api/v1/looks
List Looks
GET
/api/v1/stock
Search stock media
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
K
Kinetune API
- Foundational (C+)60/100
84
Foundational Compliance69
Developer Experience & Jentic Compatibility35
AI-Readiness & Agent Experience94
Agent Usability75
Security68
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
84
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
96%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
42%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
69
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
75%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
35
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
77%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
61%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
75
Security
Trust, risk posture, and security compliance.
Grade: A-Signals: 1
75%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
68
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B+Signals: 1
68%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Kinetune by hand means handling a bearer key or OAuth scopes such as videos:write, matching quote and create payloads, and polling or signing callbacks for finished videos. Through Jentic you install once, import Kinetune from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Kinetune puts the song, artist, Look, and video ids in the URL path (/api/v1/songs/{song_id}, /api/v1/videos/{video_id}), so a rule can pin your agent to one song or one video and the operations you pick. You choose the operations it may call, so destructive ones like archiving a song or deleting a Look are not included unless you add them.
Credential isolation
Your Kinetune key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'make a lyric video' or 'quote a Spotify Canvas', and Jentic returns the matching Kinetune operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Kinetune API through Jentic.
What authentication does the Kinetune API use?
Per its OpenAPI spec, the Kinetune API accepts a bearer token, either an organization API key beginning kt_live_ or an OAuth access token, and also declares an OAuth 2.0 authorization code flow with scopes such as videos:read, videos:write, music:read, and library:write. Through Jentic the token is stored encrypted by your own Jentic One instance and attached at execution time.
Can I find out what a lyric video will cost before rendering it?
Yes. POST /api/v1/quotes prices a lyric video or a Canvas using the same options you would send to POST /api/v1/videos. Quote and create with the same callback_url and metadata values, then create the video once the quote looks right; GET /api/v1/account shows your credit balance.
What are the rate limits for the Kinetune API?
The OpenAPI spec does not specify rate limits. Check the Kinetune documentation at https://kinetune.com for current limits before running large batches of renders.
Is there a Kinetune MCP server?
You don't need an MCP server to give your agent the Kinetune API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the quote, render, and song operations on demand without loading another server's tool definitions into its context.
How do I render a Spotify Canvas through Jentic?
Search Jentic for 'create a Spotify Canvas', load the Kinetune quote operation and call it for your song, then load POST /api/v1/videos and submit the Canvas with the same options. Poll GET /api/v1/videos/{video_id} or pass a callback_url to receive the finished file. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Kinetune API?
Yes. For example, write a rule that allows only the quote operation, the video create operation, and GET /api/v1/videos/{video_id}, so the agent can price, render, and check videos but cannot archive songs or delete Looks. Every call it makes through your instance is logged.
Can I retry or cancel a Kinetune video?
Yes. POST /api/v1/videos/{video_id}/cancel stops a video in progress and POST /api/v1/videos/{video_id}/retry makes it again. DELETE /api/v1/videos/{video_id} removes a video you no longer need.
GET STARTED