For Agents
Programmatically submit audio/video for transcription. Covers 1 operations with apiKey authentication.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Speechnotes 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://jentic.com/install.sh?src=apis&api=%2Fapis%2Fspeechnotes.co%2Fspeechnotes" | shStep 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%2Fspeechnotes.co%2Fspeechnotes" | 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 Speechnotes API.
Submit audio/video for transcription
Manage ai ml data programmatically
Integrate Speechnotes API into automated workflows
Query and filter Speechnotes API records by parameters
GET STARTED
Use for: I need to submit audio/video for transcription, Find available ai ml operations, Get the current status of Speechnotes API resources, List all records from Speechnotes API
Not supported: Does not handle payments, communications, or crm - use for ai and machine learning only.
Speech-to-text transcription API for converting audio and video files to text. The API exposes 1 endpoints secured with apiKey authentication.
Monitor Speechnotes API operational status and events
Patterns agents use Speechnotes API for, with concrete tasks.
★ AI and Machine Learning Operations
Use the Speechnotes API to perform ai ml operations programmatically. The API provides 1 endpoints covering core functionality including submit audio/video for transcription.
Call POST /transcribe to submit audio/video for transcription
Data Retrieval and Monitoring
Query Speechnotes API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.
Poll the primary Speechnotes API endpoint, compare response to last known state, and alert if changed
AI Agent Integration via Jentic
AI agents discover and call Speechnotes API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'submit audio/video for transcription', load the operation schema, and execute with Jentic-managed credentials
1 endpoints — speech-to-text transcription api for converting audio and video files to text.
METHOD
PATH
DESCRIPTION
/transcribe
Submit audio/video for transcription
/transcribe
Submit audio/video for transcription
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Speechnotes API by hand means sending your key in the X-API-Key header and constructing the transcribe request yourself. Through Jentic you install once, import the Speechnotes API from the API Directory, store the key once, and your agent calls it.
Permission scoping
The Speechnotes API exposes a single transcribe operation with its input in the request body, so limit the agent to the operations it needs, which here is submitting audio for transcription. You choose the operations it may call, so it only does what you allow and nothing more.
Credential isolation
Your Speechnotes 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.
Intent-based discovery
Agents search Jentic by intent such as 'submit audio for transcription', and Jentic returns the matching Speechnotes operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Speechnotes API through Jentic.
What authentication does the Speechnotes API use?
The Speechnotes API uses an API key passed in the `X-API-Key` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I submit audio/video for transcription with the Speechnotes API?
Yes. Use the POST /transcribe endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Speechnotes API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I submit audio/video for transcription through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'submit audio/video for transcription'. Jentic returns the matching Speechnotes API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Speechnotes API have?
The Speechnotes API exposes 1 endpoints covering transcription operations.
Can I limit what my agent is allowed to do with the Speechnotes API?
Yes. The Speechnotes API exposes a single operation, POST /transcribe, which submits audio or video for transcription. Because Jentic One is self-hosted, you decide which operations and credentials your agent may use, so you can allow it to call only /transcribe and nothing else. The stored API key is injected at execution time under your own rules, keeping the agent scoped to exactly the transcription work you permit.