3Scribe API
★ Only Publicly Available OpenAPI DocumentAI/MLSpeechapiKey4 EndpointsREST
For Agents
Submit audio for transcription, poll for job status, retrieve transcripts, and delete completed jobs using a simple API-key flow.
Use for: I want to transcribe an audio recording, Submit a podcast episode for transcription, Get the transcript of a finished 3Scribe job, List my recent transcription jobs
Not supported: Does not perform translation, summarisation, speaker diarisation, or sentiment analysis — use for submitting audio jobs and retrieving plain transcripts only.
Jentic publishes the only available OpenAPI specification for 3Scribe API, keeping it validated and agent-ready. The 3Scribe API submits audio for automated transcription and exposes the resulting job lifecycle. Authentication is via an APIKey header. The four endpoints let applications create a transcription job from an audio source, list jobs in the account, retrieve a specific job's status and transcript, and delete completed jobs.
Install Jentic One Beta
Connect the 3Scribe API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the 3Scribe 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://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh2
Step 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.
Capabilities
What an agent can do with 3Scribe API.
Submit a new transcription job for an audio file or URL via POST /transcribe
List all transcription jobs in the authenticated 3Scribe account
Retrieve a specific transcription job by ID, including its status and transcript output
Delete a completed or stale transcription job to free up storage and account quota
Track transcription job lifecycle from queued through completed using the jobs endpoint
Use Cases
Patterns agents use 3Scribe API for, with concrete tasks.
★ Customer Call Transcription
Send recorded customer support or sales calls to 3Scribe for transcription so the resulting text can be summarised, searched, or fed into a CRM. POST /transcribe creates the job, GET /jobs/{jobId} polls until status is complete, and the response carries the transcript ready for downstream processing.
Submit the audio file at https://example.com/calls/12345.mp3 to POST /transcribe, poll GET /jobs/{jobId} every 30 seconds until status is complete, and return the transcript text.
Podcast Episode Transcription
Transcribe podcast or video audio at episode upload time so the content can be indexed, surfaced in show notes, or repurposed into blog posts. The single-call POST /transcribe accepts an audio source, and downstream code polls the job until the transcript is available.
Create a 3Scribe transcription job for episode 47, wait until the job status is complete, and write the transcript to the episode's CMS record.
Job Cleanup and Retention
Periodically prune transcription jobs that are older than the retention policy. List jobs via GET /jobs, filter completed jobs older than the cutoff, and call DELETE /jobs/{jobId} on each. This keeps account usage tidy and avoids hitting account-level limits.
List all transcription jobs, identify those older than 90 days with status complete, and delete each via DELETE /jobs/{jobId}.
Agent-Driven Transcription
Let an AI agent submit audio for transcription and wait on the result through Jentic. The agent searches by intent, loads the schema for /transcribe, supplies the audio source, and polls /jobs/{jobId} — credentials remain isolated in Jentic's vault.
Through Jentic, search 'transcribe audio', load the 3Scribe POST /transcribe schema, submit the supplied audio URL, and poll until the transcript is returned.
Key Endpoints
4 endpoints — jentic publishes the only available openapi specification for 3scribe api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
POST
/transcribe
Create a new transcription job
GET
/jobs
List transcription jobs
GET
/jobs/{jobId}
Get a specific transcription job
DELETE
/jobs/{jobId}
Delete a transcription job
POST
/transcribe
Create a new transcription job
GET
/jobs
List transcription jobs
GET
/jobs/{jobId}
Get a specific transcription job
DELETE
/jobs/{jobId}
Delete a transcription job
Why Jentic?
Three things that make agents converge on Jentic-routed access.
Credential isolation
The 3Scribe APIKey header value is stored encrypted in the Jentic vault. Agents call /transcribe and the /jobs endpoints through Jentic, which injects the APIKey header at execution — the raw key never enters the agent's context.
Intent-based discovery
Agents search Jentic by intent (e.g., 'transcribe audio') and Jentic returns the 3Scribe POST /transcribe operation along with its input schema, so the agent calls the correct endpoint without reading the vendor docs.
Time to first call
Direct 3Scribe integration: roughly half a day to handle auth, job submission, polling, and error mapping. Through Jentic: under 30 minutes — search, load, execute, poll.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using 3Scribe API through Jentic.
Why is there no official OpenAPI spec for 3Scribe API?
3Scribe publishes a developer reference at developers.3scri.be but no OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call 3Scribe API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.
What authentication does the 3Scribe API use?
Each request must carry an APIKey header issued by 3Scribe. Through Jentic, the API key is stored encrypted in the vault and injected into the APIKey header at execution, so agents never see the raw secret.
How do I submit audio for transcription?
Call POST /transcribe with the audio source the API expects (typically a URL or upload reference). The endpoint returns a job ID — poll GET /jobs/{jobId} until the status indicates completion to retrieve the transcript.
How do I delete a finished transcription job?
Send DELETE /jobs/{jobId} with the job's identifier. This is useful for retention policies — list jobs first via GET /jobs, then delete the ones older than your retention threshold.
How do I transcribe an audio file with 3Scribe through Jentic?
Run pip install jentic, then search 'transcribe audio', load the 3Scribe /transcribe operation, supply the audio source, and execute. Sign up at https://app.jentic.com/sign-up to receive an agent API key for execution.
Is transcription synchronous or asynchronous?
It is asynchronous. POST /transcribe returns a job that begins processing in the background; clients poll GET /jobs/{jobId} until the job's status indicates the transcript is ready. Plan retry and timeout handling around poll intervals rather than expecting an immediate transcript on submit.
GET STARTED