canonical: https://jentic.com/apis/speakai.co/speakai

# Speak Ai API

Speak Ai API for programmatic media upload, transcription, insights extraction, folder management, recorder management, embeds, webhooks, automations, and user administration. The API exposes 64 endpoints secured with apiKey authentication.

## For AI agents

Programmatically get access token, refresh token. Covers 64 operations with apiKey authentication.

## Scope

Does not handle payments, communications, or crm - use for ai and machine learning only.

## Capabilities

- Get Access Token
- Refresh Token
- Upload media file
- List media files
- Monitor Speak Ai API operational status and events

## Use cases

### AI and Machine Learning Operations

Use the Speak Ai API to perform ai ml operations programmatically. The API provides 64 endpoints covering core functionality including get access token, refresh token, get a signed url for upload.

Example prompt: Call POST `/auth/accessToken` to get access token

### Automated Admin Management

Automate admin operations by combining multiple Speak Ai API endpoints. Agents can refresh token and then get a signed url for upload in a single workflow.

Example prompt: Call POST `/auth/refreshToken` to refresh token, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Speak Ai 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.

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

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/auth/accessToken` | Get Access Token |
| POST | `/auth/refreshToken` | Refresh Token |
| GET | `/media/upload/signedurl` | Get a Signed URL for upload |
| POST | `/media/upload` | Upload media file |
| GET | `/media` | List media files |
| GET | `/media/insight/{mediaId}` | Get media insights |
| GET | `/media/transcript/{mediaId}` | Get media transcript |
| PUT | `/media/speakers/{mediaId}` | Update transcript speakers |

## Key resources

- **Admin** — Operations for admin
- **Auth** — Operations for auth
- **Automations** — Operations for automations
- **Embed** — Operations for embed
- **Export** — Operations for export

## Why Jentic

- **Setup:** Wiring Speak Ai by hand means running its token exchange to get and refresh an Authorization key, then coordinating signed-url uploads and media, transcript, and folder operations yourself. Through Jentic you install once, import the Speak Ai API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Speak Ai puts the media id in the URL path (`/media/insight/{mediaId}`, `/media/transcript/{mediaId}`), so a rule can pin your agent to one media item: it reads insights and transcripts for that item and nothing else. You choose the operations it may call, so destructive ones like deleting media or a folder are not included unless you add them.
- **Credential handling:** Your Speak Ai 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 'get a signed upload url' or 'read a media transcript', and Jentic returns the matching Speak Ai operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Openai** — Alternative ai ml API
- **Anthropic** — Alternative ai ml API
- **Cohere** — Complementary ai ml API
- **Huggingface** — Complementary ai ml API

## FAQ

### What authentication does the Speak Ai API use?

The Speak Ai API uses an API key passed 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 access token with the Speak Ai API?

Yes. Use the POST `/auth/accessToken` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Speak Ai 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 get access token through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get access token'. Jentic returns the matching Speak Ai API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Speak Ai API have?

The Speak Ai API exposes 64 endpoints covering admin, auth, automations operations.

### Can I limit what my agent is allowed to do with the Speak Ai API?

Yes. Because you run Jentic One yourself, your own rules decide which Speak Ai operations and credentials the agent can use. Speak Ai puts the media id in the URL path, as in GET `/media/insight/{mediaId}` and GET `/media/transcript/{mediaId}`, so a rule can pin the agent to a single media item and let it read only that item's insights and transcript. You also choose the operations it may call, so destructive ones such as deleting media or a folder stay off unless you add them.