canonical: https://jentic.com/apis/aimastering.com/aimastering # AI Mastering API Jentic publishes the only available OpenAPI specification for AI Mastering API, keeping it validated and agent-ready. AI Mastering is an automated audio mastering service that uses machine learning to master music tracks. The API exposes mastering jobs, audio uploads and downloads, and an account plans listing. The flow is upload an audio file, create a mastering job, and download the resulting mastered audio. Authentication uses an API key. ## For AI agents Upload audio files, create AI mastering jobs, retrieve job status, and download mastered audio. ## Scope Does not handle music distribution, royalty management, or stem separation - use for AI mastering of complete mixed audio tracks only. ## Capabilities - Upload an audio file via POST /audios so it can be referenced by mastering jobs - Create an AI mastering job for an uploaded audio through POST /masterings - Poll mastering progress with GET /masterings/{id} until the job reports completion - Download the original or mastered audio file via GET /audios/{id}/download - List the authenticated user's mastering jobs with GET /masterings - List available subscription plans through GET /plans for billing-aware integrations ## Use cases ### Bedroom Producer Mastering Workflow Independent producers upload mixdowns and receive AI-mastered tracks suitable for streaming. Upload via /audios, create the job via /masterings referencing the uploaded id, poll /masterings/{id} until done, and download via /audios/{id}/download. The full loop runs in minutes per track without a human mastering engineer. Example prompt: POST a mixdown to /audios, POST a /masterings job referencing the audio id, poll /masterings/{id}, and GET /audios/{id}/download once complete ### Batch Mastering for a Catalogue A label batches dozens of tracks for AI mastering ahead of release. Upload each track to /audios, queue a /masterings job per track, and use GET /masterings to track aggregate progress. The catalogue is delivered as mastered audio without per-track human session time. Example prompt: Iterate the catalogue, POST each track to /audios and /masterings, then poll /masterings to find finished jobs and download each via /audios/{id}/download ### Plan-Aware Self-Service App A web app exposes AI Mastering to end users with plan-based limits. Read /plans to surface upgrade options, and gate mastering job creation by the user's plan. The /plans endpoint provides the data needed to render pricing and feature comparisons inside the app. Example prompt: GET /plans, render the available tiers in the app, and only call /masterings if the current user's plan allows another job ### Agent-Driven Mastering via Jentic An AI agent submits a mix for mastering, polls for completion, and notifies the user with the download link. Through Jentic the agent searches for the right operation, the API key is supplied from the vault, and the agent never sees the raw key. Example prompt: Use Jentic search 'master an audio track', execute /audios upload, /masterings job creation, poll /masterings/{id}, and post the /audios/{id}/download URL to the user ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | /audios | Upload an audio file | | GET | /audios/{id} | Get audio details | | GET | /audios/{id}/download | Download an audio file | | POST | /masterings | Create a mastering job | | GET | /masterings | List mastering jobs | | GET | /masterings/{id} | Get a mastering job's status | | GET | /plans | List available subscription plans | ## Key resources - **Audios** — Audio file uploads, lookup, and download endpoints - **Masterings** — Mastering jobs created against uploaded audio with progress lookup - **Plans** — Available subscription plans for the AI Mastering service ## Why Jentic - **Setup:** Wiring AI Mastering by hand means uploading audio, polling mastering jobs, downloading results, and writing your own retry logic across those steps. Through Jentic you install once, import AI Mastering from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** AI Mastering puts the audio and mastering ids in the URL path (/audios/{id}, /masterings/{id}), so a rule can pin your agent to the resources it created. You choose the operations it may call, so it can upload and master without listing every plan or other job. - **Credential handling:** Your AI Mastering API 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. - **Discovery method:** Agents search Jentic by intent such as 'master an audio track', and Jentic returns the AI Mastering /masterings operation alongside the upstream /audios upload with their schemas so the agent chains the flow without browsing the reference docs. ## Related APIs - **Replicate API** — General-purpose hosted ML model API including audio models - **Hugging Face Inference API** — Hosted inference for community audio and music models - **Cloudmersive API** — Media utility API that complements mastering with format conversion and inspection ## FAQ ### Why is there no official OpenAPI spec for AI Mastering API? AI Mastering does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the AI Mastering API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer. ### What authentication does the AI Mastering API use? An apiKey scheme. The key is sent as a header on every request. Through Jentic the key is held in the vault and never enters the agent's context. ### Can I master an audio track end to end via the API? Yes. POST the audio file to /audios, create a mastering job by POST /masterings referencing the audio id, poll GET /masterings/{id} for completion, then GET /audios/{id}/download for the mastered output. ### What are the rate limits for the AI Mastering API? The spec does not declare explicit rate limits. The /masterings list endpoint accepts a page parameter for paginated retrieval, and you should respect HTTP error codes returned by the server when running batches. ### How do I list available plans through Jentic? Run pip install jentic, search 'list AI Mastering plans', and execute /plans. The response can drive a pricing UI or a programmatic plan-gate. Run it through Jentic One, the self-hosted execution layer. ### Can I download both the original and mastered audio? Yes. /audios/{id}/download returns the audio file. Each uploaded audio and each mastering output has its own audio id, so you can retrieve either by id. ### Can I limit what my agent is allowed to do with the AI Mastering API? Yes. Because you run Jentic One yourself, your own rules decide which AI Mastering operations and credentials the agent may use, so you can allow it to upload audio via POST /audios and create jobs via POST /masterings while blocking calls it should not make, such as GET /plans or listing every job. Since the audio and mastering ids sit in the URL path (/audios/{id}, /masterings/{id}), you can pin the agent to the resources it created rather than any arbitrary id. The API key is injected at execution time and never enters the agent's prompt or context, so the agent acts only within the bounds you set.