For Agents
Run automatic audio post-production: create a production, upload audio, attach a preset, start processing, and retrieve the cleaned-up output via a Bearer or Basic-authenticated REST API.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Auphonic 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.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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.
What an agent can do with Auphonic API.
Create a new production with POST /productions.json and attach a preset
Upload an audio file to a production via POST /production/{uuid}/upload.json
Start automatic post-production with POST /production/{uuid}/start.json
GET STARTED
Use for: Create a new Auphonic production for a podcast episode, Upload a recorded interview to a production for processing, Start audio post-production on an existing production, Apply a saved preset to a new production
Not supported: Does not handle hosting, RSS feed publishing, or distribution - use for automatic audio post-production, presets, and rendered output retrieval only.
Auphonic is an automatic audio post-production service that handles loudness normalisation, leveling, noise and hum reduction, filtering, and multi-format encoding for podcasters, journalists, and video producers. The API exposes the full production lifecycle: create a production, upload an audio file or pull from a service, attach a preset, start processing, and retrieve the rendered output. The spec behind this page declares 17 operations covering productions, presets, account info, and reference data such as production status codes and supported external service types. It is a Jentic-authored spec scoped to the core production and preset lifecycle, and two of the operations it declares (a production reset call and an output-file-endings lookup) are not present on the live API. Auphonic also publishes its own larger OpenAPI 3.0.3 document at auphonic.com/help/openapi.yaml.
List, create, update, and delete reusable presets via /presets.json and /preset/{uuid}.json
Fetch the current authenticated user's account info from GET /user.json
Look up production status codes and supported external service types via GET /info/production_status.json and GET /info/service_types.json
Patterns agents use Auphonic API for, with concrete tasks.
★ Podcast post-production pipeline
Podcast teams want every recorded episode cleaned up consistently without manual mixing. The agent calls POST /productions.json with a preset field that names the preset capturing the show's loudness target and output formats, uploads the raw recording via POST /production/{uuid}/upload.json, and triggers POST /production/{uuid}/start.json. Once Auphonic finishes, GET /production/{uuid}.json returns the rendered file URLs, ready for the publishing step.
Create a production via POST /productions.json with a known preset UUID in the preset field, upload the source file with POST /production/{uuid}/upload.json, then call POST /production/{uuid}/start.json and poll GET /production/{uuid}.json until status_string='Done' (status 3).
Bulk archive cleanup
Radio stations and journalism archives sit on years of variably mastered recordings. An agent can iterate through stored files, create one production per file, attach a 'speech' preset, and process them through Auphonic to produce a normalised archive. /info/production_status.json gives the full set of status codes up front, so the agent can tell a finished production from a failed one and requeue only the failures in a second pass.
For each WAV in a working folder, POST /productions.json with a speech preset, upload via POST /production/{uuid}/upload.json, and start processing. After completion, write the output URL to a manifest file.
Show-specific preset management
Multi-show studios need different loudness handling and different output formats for each show. /presets.json lists, creates, and deletes presets, and /preset/{uuid}.json updates one in place. An admin agent can keep the preset directory aligned with each show's spec without anyone touching the Auphonic web UI.
Update preset 'show-flagship' via POST /preset/{uuid}.json to set algorithms.normloudness=true and an output_files entry with format and bitrate, then verify with GET /preset/{uuid}.json.
AI agent integration via Jentic
A media-ops agent built on Jentic can run an Auphonic production without holding the Bearer token in its context. The agent searches an intent like 'process a podcast through Auphonic', Jentic returns the matching production-creation operation with its input schema, and execution uses the token resolved from your Jentic One instance. The full chain (create, upload, start, poll) is orchestrated as one workflow.
Use Jentic search 'create an Auphonic production', load the schema for POST /productions.json, and execute it with a preset UUID and metadata for a new episode.
17 endpoints — auphonic is an automatic audio post-production service that handles loudness normalisation, leveling, noise and hum reduction, filtering, and multi-format encoding for podcasters, journalists, and video producers.
METHOD
PATH
DESCRIPTION
/productions.json
List all productions
/productions.json
Create a new production
/production/{uuid}/upload.json
Upload an audio file to a production
/production/{uuid}/start.json
Start processing a production
/production/{uuid}.json
Get one production including its status and rendered output files
/presets.json
List all presets
/presets.json
Create a preset
/user.json
Get the current user's account info
/productions.json
List all productions
/productions.json
Create a new production
/production/{uuid}/upload.json
Upload an audio file to a production
/production/{uuid}/start.json
Start processing a production
/production/{uuid}.json
Get one production including its status and rendered output files
Three things that make agents converge on Jentic-routed access.
Credential isolation
Your Auphonic basic or bearer credential is stored once, encrypted, by your own Jentic One instance, refreshed automatically, and injected at execution time. The raw secret never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create an Auphonic production', and Jentic returns the matching operation with its input schema so the agent calls /productions.json, /production/{uuid}/start.json, or /presets.json without reading the reference docs.
Time to first call
Alternatives and complements available in the Jentic catalogue.
Specific to using Auphonic API through Jentic.
Does Auphonic publish an official OpenAPI spec?
Yes. Auphonic serves an OpenAPI 3.0.3 document at auphonic.com/help/openapi.yaml, linked from its API documentation at auphonic.com/help/api as 'OpenAPI Specification' and rendered with ReDoc. It declares 36 paths and 60 operations. The spec behind this page is a Jentic-authored spec covering 17 operations of the core production and preset lifecycle, two of which (a production reset call and an output-file-endings lookup) are not present on the live API; the vendor resets a production with a reset_data flag on POST /production/{uuid}.json instead. Reach for the vendor document when you need the wider surface such as chapters, cuts, webhooks, or outgoing services. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there an Auphonic MCP server?
You don't need an MCP server to give your agent Auphonic. Jentic connects it directly from the API Directory: import it, store your Auphonic credential once, and your agent calls the production and preset operations it needs. Operations are discovered on demand, so no extra server's tool definitions sit in the agent's context.
What authentication does the Auphonic API use?
Auphonic documents three schemes: API key authentication, HTTP Basic authentication, and OAuth 2.0. API key authentication sends the key as a bearer token in an Authorization header and is Auphonic's recommended method for your own resources. HTTP Basic uses the account's username and password. OAuth 2.0 is intended for third-party applications acting for multiple Auphonic accounts; Auphonic documents it, but it is not declared in the spec behind this page. Through Jentic the credential is held by your own Jentic One instance and injected at execution time.
Can I run automatic post-production on a single file with the Auphonic API?
Yes. Create a production via POST /productions.json with a preset UUID in the preset field, upload the file via POST /production/{uuid}/upload.json, and trigger POST /production/{uuid}/start.json. Poll GET /production/{uuid}.json until status_string='Done' (status 3) and read the output URLs from the response.
What are the rate limits for the Auphonic API?
Auphonic documents per-operation limits in its own OpenAPI document and returns 429 when one is exceeded. Listing productions and fetching a single production allow 60 requests per 4 minutes each. Creating a production allows 40 requests per 2 minutes, or 100 for business accounts. Downloads allow 30 per 5 minutes per production. For frequent status checks Auphonic points you at webhooks rather than polling.
How do I attach a saved preset to a new production through Jentic?
Run jentic search 'create an Auphonic production', load the schema for POST /productions.json, and pass the preset field in the body. The bearer token is resolved from your Jentic One instance at execution time.
Is the Auphonic API free?
Auphonic is free for 2 hours of processed audio per month. Recurring credit plans run from 9 hours to 250 hours per month, with one-time credits available as well. What you pay for is processing volume; the per-operation request limits above apply on top of it.
Can I limit what my agent is allowed to do with the Auphonic API?
Yes. Because you run Jentic One yourself, your own rules decide which Auphonic operations and credentials the agent may use. Auphonic puts the production UUID in the URL path, such as POST /production/{uuid}/upload.json and POST /production/{uuid}/start.json, so you can pin the agent to uploads and starts for a single production. You choose the operations it may call, so a destructive action like DELETE /production/{uuid}.json stays out of reach unless you add it.
/presets.json
List all presets
/presets.json
Create a preset
/user.json
Get the current user's account info