# Upload Media — Speak AI

> Upload an audio or video file to Speak AI for transcription and analysis, from a publicly reachable URL or an AWS signed URL. Processing is asynchronous, so use the New Automated Transcription (Instant) trigger to act on the result. See…

- Key: `speak_ai-upload-media`
- Type: Action (Write)
- Version: 0.0.4
- App: Speak AI (`speak_ai`) — https://pipedream.com/apps/speak-ai.md
- This page (HTML): https://pipedream.com/apps/speak-ai/actions/upload-media
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/speak_ai/actions/upload-media/upload-media.mjs

## Description

Upload an audio or video file to Speak AI for transcription and analysis, from a publicly reachable URL or an AWS signed URL. Processing is asynchronous, so use the **New Automated Transcription (Instant)** trigger to act on the result. [See the documentation](https://docs.speakai.co/api/media/#post-media-upload).

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `name` | `string` | Yes | Name of the media file |
| `url` | `string` | Yes | Public URL or AWS signed URL |
| `mediaType` | `string` | Yes | Type of media file (audio or video) |
| `folderId` | `string` | Yes | A Speak AI folder ID, e.g. 905c208f1c07. The folder to upload to, or to retrieve files from. Returned as folderId by List Folder ID Options Options are loaded from the connected account. |
| `description` | `string` | No | Description of the media file |
| `tags` | `string[]` | No | Optional metadata tags for the media file upload |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "speak_ai",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "speak_ai-upload-media",
  arguments: {
    name: "Name",
    url: "URL",
  },
})
```

**TypeScript**

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "speak_ai-upload-media",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    speak_ai: { authProvisionId: "apn_xxxxxxx" },
    name: "Name",
    url: "URL",
  },
})

console.log(result)
```

**cURL**

```bash
curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "speak_ai-upload-media",
    "configured_props": {
      "speak_ai": { "authProvisionId": "apn_xxxxxxx" },
      "name": "Name",
      "url": "URL"
    }
  }'
```

---

- App: https://pipedream.com/apps/speak-ai.md · All apps: https://pipedream.com/apps