canonical: https://jentic.com/apis/rev.ai/asynchronous-speech-to-text-api-documentation

# Rev Asynchronous Speech-To-Text API Documentation

Rev.ai provides quality speech-text recognition via a RESTful API. All public methods and objects are documented here for developer reference. For a real-time speech to text solution, use Rev.ai's [Streaming API](/docs/streaming). Base Endpoint The base url for this version of the API is > `https://api.rev.ai/speechtotext/v1` All endpoints described in this documentation are relative to this base . The API exposes 7 endpoints secured with bearer authentication.

## For AI agents

Programmatically get account, submit transcription job. Covers 7 operations with bearer authentication.

## Scope

Does not handle payments, communications, or crm - use for hr and recruiting only.

## Capabilities

- Get Account
- Submit Transcription Job
- Delete Job by Id
- Query and filter Asynchronous Speech-To-Text API Documentation records by parameters
- Monitor Asynchronous Speech-To-Text API Documentation operational status and events

## Use cases

### HR and Recruiting Operations

Use the Asynchronous Speech-To-Text API Documentation to perform hr recruiting operations programmatically. The API provides 7 endpoints covering core functionality including get account, submit transcription job, get list of jobs.

Example prompt: Call GET /account to get account

### Automated Account Management

Automate account operations by combining multiple Asynchronous Speech-To-Text API Documentation endpoints. Agents can submit transcription job and then get list of jobs in a single workflow.

Example prompt: Call POST /jobs to submit transcription job, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Asynchronous Speech-To-Text API Documentation 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 bearer tokens manually.

Example prompt: Search Jentic for 'get account', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | /account | Get Account |
| POST | /jobs | Submit Transcription Job |
| GET | /jobs | Get List of Jobs |
| GET | /jobs/{id} | Get Job By Id |
| DELETE | /jobs/{id} | Delete Job by Id |
| GET | /jobs/{id}/captions | Get Captions |
| GET | /jobs/{id}/transcript | Get Transcript By Id |

## Key resources

- **Account** — Operations related to Account
- **Captions** — Operations related to Captions
- **Jobs** — Operations related to Jobs
- **Transcript** — Operations related to Transcript

## Why Jentic

- **Setup:** Wiring the Rev AI Asynchronous Speech-To-Text API by hand means learning its bearer token auth, targeting the api.rev.ai/speechtotext/v1 host, and polling transcription jobs yourself. Through Jentic you install once, import the Asynchronous Speech-To-Text API from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** The Asynchronous Speech-To-Text API puts the job id in the URL path (/jobs/{id}/...), so a rule can pin your agent to one job: it can read that job's transcript and captions and nothing else. You choose the operations it may call, so destructive ones like job deletion are not included unless you add them.
- **Credential handling:** Your Rev AI token 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 'submit a transcription job' or 'get a job's transcript', and Jentic returns the matching Asynchronous Speech-To-Text API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Greenhouse** — Alternative hr recruiting API
- **Lever** — Alternative hr recruiting API
- **Workday** — Complementary hr recruiting API

## FAQ

### What authentication does the Asynchronous Speech-To-Text API Documentation use?

The Asynchronous Speech-To-Text API Documentation uses a Bearer token in the Authorization 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 get account with the Asynchronous Speech-To-Text API Documentation?

Yes. Use the GET /account endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Asynchronous Speech-To-Text API Documentation?

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 get account through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get account'. Jentic returns the matching Asynchronous Speech-To-Text API Documentation operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Asynchronous Speech-To-Text API Documentation have?

The Asynchronous Speech-To-Text API Documentation exposes 7 endpoints covering account, captions, jobs operations.

### Can I limit what my agent is allowed to do with the Rev AI Speech-To-Text API?

Yes. Because you run Jentic One yourself, your own rules decide which operations and credentials the agent may use. Since this API puts the job id in the URL path (/jobs/{id}/...), you can pin the agent to a single job so it only reads that job's transcript and captions and nothing else. You choose the operations it may call, so destructive ones like DELETE /jobs/{id} stay out of reach unless you explicitly add them.