# Speak AI — Pipedream Connect

> Transcribe, translate, and analyze with AI

- API slug: `speak_ai` (use in MCP headers and tool keys)
- Auth: OAuth (Pipedream-managed)
- Categories: Artificial Intelligence (AI)
- Website: https://speakai.co/
- This page (HTML): https://pipedream.com/apps/speak-ai
- Tools: 6 actions · 7 triggers

## Connect via MCP (recommended)

- Endpoint: `https://remote.mcp.pipedream.net/v3`
- Headers: `Authorization: Bearer <token>` · `x-pd-project-id` · `x-pd-environment` · `x-pd-external-user-id` · `x-pd-app-slug: speak_ai`

```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()

// e.g. run Analyze Text:
const result = await mcp.callTool({
  name: "speak_ai-analyze-text",
  arguments: {
    folderId: "Folder ID",
    mediaId: "Media ID",
  },
})
```

Docs: [MCP guide](https://pipedream.com/docs/connect/mcp/developers.md)

## SDK

```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-analyze-text",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    speak_ai: { authProvisionId: "apn_xxxxxxx" },
    folderId: "Folder ID",
    mediaId: "Media ID",
  },
})
```

Docs: [Managed auth guide](https://pipedream.com/docs/connect/managed-auth/quickstart.md) · [Tools guide](https://pipedream.com/docs/connect/components.md)

## Actions (6)

### `speak_ai-analyze-text` — Analyze Text (Read-only)

Retrieve the insights Speak AI generated for a text note: sentiment, keywords and named entities. Takes the media ID of a text note that already exists in Speak AI. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/actions/analyze-text.md

### `speak_ai-find-media` — Find Media (Read-only)

Look up a single Speak AI media file by its ID and return everything stored against it: transcript, sentiment, keywords, topics and metadata. Use Get Transcription instead when only the transcript is needed. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/actions/find-media.md

### `speak_ai-get-transcription` — Get Transcription (Read-only)

Retrieve just the transcript of a processed Speak AI media file, as an array of speaker-attributed segments. Use Find Media instead to get sentiment, keywords and the rest of the analysis. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/actions/get-transcription.md

### `speak_ai-list-folder-id-options` — List Folder ID Options (Read-only)

Retrieves available options for the Folder ID field. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/actions/list-folder-id-options.md

### `speak_ai-run-ai-chat` — Run AI Chat (Write)

Ask a question about Speak AI media and get the answer back. Scope the question to specific media files, to a whole folder, or to both. Answers are only as good as the prompt, so be specific about the output wanted. Media must finish analyzing first. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/actions/run-ai-chat.md

### `speak_ai-upload-media` — Upload Media (Write)

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.

Full schema: https://pipedream.com/apps/speak-ai/actions/upload-media.md

## Triggers (7)

### `speak_ai-new-ai-chat` — New AI Chat Response (Instant) (Instant)

Emit new event when a Speak AI Chat response is ready (chat.status). See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-ai-chat.md

### `speak_ai-new-transcription` — New Automated Transcription (Instant) (Instant)

Emit new event when Speak AI finishes transcribing a media file (media.analyzed, media.reanalyzed). See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-transcription.md

### `speak_ai-new-captions` — New Captions (Instant) (Instant)

Emit new event with the caption file (SRT or VTT) when Speak AI finishes analyzing a media file (media.analyzed, media.reanalyzed). See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-captions.md

### `speak_ai-new-media-created-instant` — New Media Created (Instant) (Instant)

Emit new event when a new media file is created. Useful for initiating workflows based on new media intake. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-media-created-instant.md

### `speak_ai-new-recording` — New Recording Captured (Instant) (Instant)

Emit new event when a recording is captured through a Speak AI embed recorder (embed_recorder.recording_received). See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-recording.md

### `speak_ai-new-sentiment` — New Sentiment Analysis (Instant) (Instant)

Emit new event when Speak AI produces sentiment analysis for a media file (media.analyzed, media.reanalyzed). See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-sentiment.md

### `speak_ai-new-text-analyzed-instant` — New Text Analyzed (Instant) (Instant)

Emit new event when a new text is analyzed. Useful for initiating workflows based on new text analysis. See the documentation.

Full schema: https://pipedream.com/apps/speak-ai/triggers/new-text-analyzed-instant.md

---

- All apps: https://pipedream.com/apps — index: https://pipedream.com/llms.txt
- Pipedream docs for agents: https://pipedream.com/docs/llms.txt