speakai-mcp

<p align="center">
  <img src="assets/logo.png" alt="Speak AI" width="120" />
</p>

<h1 align="center">Connect Speak AI to Claude or ChatGPT in 60 seconds</h1>

<p align="center">
  <strong>For researchers, revenue teams, meeting-heavy teams, and media workflows.</strong><br/>
  No Terminal. No npm. No JSON config files.
</p>

<p align="center">
  <a href="https://docs.speakai.co/mcp"><strong>Installation guide at docs.speakai.co/mcp →</strong></a>
</p>

<p align="center">
  <a href="https://www.npmjs.com/package/@speakai/mcp-server"><img src="https://img.shields.io/npm/v/@speakai/mcp-server" alt="npm version" /></a>
  <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-compatible-blue" alt="MCP compatible" /></a>
  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT" /></a>
</p>

---

## What this does

Speak AI transcribes your interviews, sales calls, research sessions, webinars, podcasts, and team meetings — then extracts AI insights like summaries, action items, sentiment, and themes.

This connector (built on MCP — the standard way Claude and ChatGPT connect to apps) brings all of that into Claude or ChatGPT. Once installed, you can ask:

- "Find the last 10 customer interviews that mention pricing, group the feedback by theme, and cite the source recordings."
- "Summarize this week's team meetings into decisions, action items, owners, and unresolved risks."
- "Pull exact customer quotes about onboarding friction from recent research calls and format them for a product brief."
- "Find a strong 30-second highlight from the latest webinar, create a clip, and export captions."

The AI does the searching, summarizing, and citing. Your recordings stay in your Speak AI workspace — Claude and ChatGPT just query them through this connector.

---

## Install (pick your tool)

> **Two paths to install** — pick whichever feels easier. The one-click connect path approves access via a permission popup; the manual path pastes an API key into a header.

> **Don't know which one to pick?** If you already use Claude or ChatGPT, install for whichever one you have.

> Speak AI's connector address (paste this into your AI tool's connector settings — it's the same idea as pasting a Zoom link into your calendar): `https://api.speakai.co/v1/mcp`

### Claude.ai (web)

1. Open [claude.ai/settings/connectors](https://claude.ai/settings/connectors)
2. Click **Add custom connector**
3. Name it **Speak AI** and paste `https://api.speakai.co/v1/mcp`, then click **Add**
4. A permission popup asks you to log into Speak AI and click **Allow**
5. Done — Speak AI shows in your connector list with its tools ready to use. Open a new chat and ask about your recordings.

<details>
<summary>What each step looks like (screenshots)</summary>

**3. Add custom connector dialog** — name and URL filled in.

![Claude add custom connector dialog](./assets/claude/1.connector.png)

**5. Connected** — Speak AI tools appear in your connector list.

![Speak AI connected in Claude](./assets/claude/2.connected.png)

</details>

<details>
<summary>Developer alternative — manual setup with an API key</summary>

Get a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys), then in step 3 expand **Advanced settings** and add `Authorization` = `Bearer <your-key>` before clicking Add.

</details>

### Claude Desktop

1. Open Claude Desktop → **Settings → Connectors → Add custom connector**
2. Paste `https://api.speakai.co/v1/mcp`
3. Click **Add** — a permission popup opens. Sign in to Speak AI and click **Allow** on the screen that appears.
4. Done.

<details>
<summary>Developer alternative — manual setup with an API key</summary>

Get a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys), then in step 2 also expand **Custom headers** and add:

- **Header name:** `Authorization`
- **Header value:** `Bearer <your-speak-api-key>`

Then click Add.

</details>

### ChatGPT

1. Open ChatGPT → **Settings → Apps & Connectors → Advanced**
2. Turn on **Developer Mode** (required while Speak AI isn't yet listed in ChatGPT's app store — this lets you add it as a custom app)
3. Back on **Apps & Connectors**, click **Create** and paste `https://api.speakai.co/v1/mcp`
4. For **Authentication**, choose **OAuth**
5. ChatGPT opens a new tab to Speak AI — sign in (or click **Confirm** if already logged in) to authorize. You'll be redirected back; close the tab and return to ChatGPT.
6. **Per-chat:** open a chat, click the **+** / connector menu, and enable **Speak AI** for that chat.

<details>
<summary>What each step looks like (screenshots)</summary>

**1. Connect screen in ChatGPT** — paste the connector URL and pick OAuth.

![ChatGPT connect screen](./assets/openai/1.connect.png)

**2. Confirm and continue** — ChatGPT asks you to continue to Speak AI.

![ChatGPT continue to Speak](./assets/openai/2.connect-continue.png)

**3. Authorize on Speak AI** — sign in or click Confirm if you're already signed in.

![Speak AI authorization screen](./assets/openai/3.speak-auth.png)

**4. Connected** — Speak AI now shows in your ChatGPT connector list.

![Speak AI connected in ChatGPT](./assets/openai/4.connected.png)

</details>

<details>
<summary>Trouble connecting?</summary>

A few things we've seen during early access:

- **Authorization tab doesn't show a "you're connected" page** — if you land on the plain Speak AI dashboard with no confirmation, the authorization still went through. Close that tab and return to ChatGPT.
- **"Connect" button keeps reopening the dashboard** — fully close and reopen ChatGPT, then check **Settings → Apps & Connectors**. Speak AI should already be listed there.
- **"No actions available" inside a chat** — make sure Developer Mode is still on, and that you've enabled Speak AI from the per-chat connector menu (step 6 above).

Still stuck? Email [success@speakai.co](mailto:success@speakai.co).

</details>

### Claude Code (terminal)

**Recommended — install from the official Claude Code plugin marketplace:**

1. Add the official marketplace (one-time): `/plugin marketplace add claude-plugins-official`
2. Install the plugin: `/plugin install speakai@claude-plugins-official`
3. Activate it: `/reload-plugins`
4. Run the `getting-started` skill and paste your Speak AI API key. Generate one at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys).

If `/plugin install` doesn't find Speak AI, refresh the local catalog with `/plugin marketplace update claude-plugins-official` and retry.

<details>
<summary>Developer alternative — manual HTTP transport</summary>

Skip the plugin and add the connector directly:

```sh
claude mcp add speakai --transport http --url https://api.speakai.co/v1/mcp
```

Claude Code will open an OAuth window for sign-in. To bypass OAuth and pass a Bearer token instead:

```sh
claude mcp add speakai --transport http --url https://api.speakai.co/v1/mcp \
  --header "Authorization: Bearer $SPEAKAI_KEY"
```

Set `SPEAKAI_KEY` in your shell first, or paste your key inline. Generate a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys).

</details>

### Cursor

[![Add to Cursor](https://img.shields.io/badge/Cursor-Install_Speak_AI-000000?logo=cursor&logoColor=white&style=for-the-badge)](cursor://anysphere.cursor-deeplink/mcp/install?name=speakai&config=eyJ1cmwiOiJodHRwczovL2FwaS5zcGVha2FpLmNvL3YxL21jcCJ9)

Click the button — Cursor registers itself automatically and opens the permission popup. Sign in to Speak AI and click **Allow**.

<details>
<summary>Developer alternative — manual setup with an API key</summary>

Use the manual stdio setup in the Developer reference at the bottom of this README.

</details>

### VS Code

[![Add to VS Code](https://img.shields.io/badge/VS_Code-Install_Speak_AI-007ACC?logo=visualstudiocode&logoColor=white&style=for-the-badge)](https://vscode.dev/redirect/mcp/install?name=speakai&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.speakai.co%2Fv1%2Fmcp%22%7D)

Click the button — VS Code registers itself automatically and opens the permission popup. Sign in to Speak AI and click **Allow**.

<details>
<summary>Developer alternative — manual setup with an API key</summary>

Use the manual stdio setup in the Developer reference at the bottom of this README.

</details>

### OpenClaw / ClawHub

Speak AI is published as a skill on ClawHub for OpenClaw-compatible agents.

1. Visit the [Speak AI skill page on ClawHub](https://clawhub.ai/skills/speakai)
2. Follow the install instructions for your agent — e.g. `clawhub install speakai` from the ClawHub CLI
3. Set your `SPEAK_API_KEY` environment variable. Generate one at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys).

### ChatGPT (API / Responses)

For developers calling the Responses API directly. Pass the bearer token in the tool config:

```json
{
  "tools": [
    {
      "type": "mcp",
      "server_url": "https://api.speakai.co/v1/mcp",
      "authorization": "Bearer YOUR_SPEAK_API_KEY"
    }
  ]
}
```

Get a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeys).

---

## Privacy & data

When you click **Allow** on the permission popup (or paste your Speak AI API key into Claude or ChatGPT), you're authorizing that AI assistant to read and modify your Speak AI workspace on your behalf — including media files, transcripts, and AI insights.

- Your recordings stay in your Speak AI workspace. They are not copied or stored by Anthropic or OpenAI.
- Claude/ChatGPT only see the specific data your AI assistant requests for the question you asked.
- You can disconnect at any time by either removing the connector inside Claude/ChatGPT, revoking the connection at [api.speakai.co/v1/oauth/connections](https://api.speakai.co/v1/oauth/connections), or rotating/revoking your