Speak AI MCP
About
Connect Claude, ChatGPT, and other AI assistants to your Speak AI workspace. Transcribe meetings, analyze media, extract insights, all through natural conversation.
Details
- Author
- speakai
- Categories
- Productivity, Other, AI
Jump to
Developer reference (CLI, API, advanced setup)
The MCP server lives athttps://api.speakai.co/v1/mcpand supports two auth methods:
- OAuth 2.1 + Dynamic Client Registration— install by pasting the URL above into any MCP client and approving the consent popup. Discovery, DCR,/authorize+ consent,/token, and revocation endpoints are all available.
- Bearer token(your Speak AI API key —Authorization: Bearer <key>header). For clients that don't speak OAuth, plus the npm CLI and stdio mode.
Get a Speak AI API key at](https://calendly.com/speak-ai/demo?utm_source=mcp&utm_medium=readme&utm_campaign=booking-cta)app.speakai.co/developers/apikeys.
The@speakai/mcp-servernpm package provides:
- A CLI (speakai-mcp) for scripting and pipelines (30 commands).
- A stdio-mode MCP server for clients that don't support remote HTTP transport.
- An auto-setup wizard that detects installed MCP clients and configures them.
npm install -g @speakai/mcp-server speakai-mcp init
Add to~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or%APPDATA%\Claude\claude_desktop_config.json(Windows):
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
export SPEAK_API_KEY="your-api-key" claude mcp add speak-ai -- npx -y @speakai/mcp-server
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
SPEAK_API_KEY=your-key npx @speakai/mcp-server
Resources provide direct data access without tool calls. Clients can read these URIs directly.
Pre-built workflow prompts that agents can invoke to run multi-step tasks.
Upload a recording and get a full analysis — transcript, insights, action items, and key takeaways.
Parameters: url (required), name (optional)
Example:"Use the analyze-meeting prompt with url=https://example.com/standup.mp3"
Search for themes, patterns, or topics across multiple recordings or your entire library.
Parameters: topic (required), folder (optional)
Example:"Use the research-across-media prompt with topic='customer churn reasons'"
Prepare a brief from recent meetings — pull transcripts, extract decisions, and summarize open items.
Parameters: days (optional, default: 7), folder (optional)
Example:"Use the meeting-brief prompt with days=14 to cover the last two weeks"
npm install -g @speakai/mcp-server speakai-mcp config set-key
- --json— output raw JSON (for scripting and piping)
- --help— show command-specific help
# Upload and wait for processing speakai-mcp upload https://example.com/interview.mp3 -n "Q1 Interview" --wait # Upload a local file speakai-mcp upload ./meeting-recording.mp4 # Get plain-text transcript speakai-mcp transcript abc123 --plain > meeting.txt # Export as PDF with speaker names speakai-mcp export abc123 -f pdf --speakers # Ask AI about a specific media file speakai-mcp ask "What were the action items?" -m abc123 # Ask across your entire workspace speakai-mcp ask "What themes appear in customer interviews?" # Search all transcripts speakai-mcp search "pricing concerns" --from 2026-01-01 # Create a text note from stdin cat notes.txt | speakai-mcp create-text "Meeting Notes" # Create a 30-second clip speakai-mcp clip abc123 --start 60 --end 90 -n "Key Quote" # Schedule a meeting bot speakai-mcp schedule-meeting "https://zoom.us/j/123456" -t "Weekly Standup" # List videos as JSON for scripting speakai-mcp ls --type video --json | jq '.mediaList[].name' # List media from the last week speakai-mcp ls --from 2026-04-18 --to 2026-04-25 # Move 3 files to a folder speakai-mcp move folder123 media1 media2 media3
You: "Upload and transcribe this recording: https://example.com/meeting.mp3" AI: I'll upload that for you and start processing. → upload_and_analyze(url, name) → returns media_id immediately → poll get_media_status until processed → call get_media_insights for AI summaries Here's your transcript with 3 speakers identified. Key insights: 5 action items, positive sentiment overall. Top topics: Q2 roadmap, hiring plan, budget review.
You: "What themes came up across all our customer interviews this month?" AI: Let me search your media library. → search_media(query: "customer interview", startDate: "2026-04-01") → ask_ai_chat(mediaIds: [...], prompt: "What are the recurring themes?") Across 12 interviews, the top themes were: 1. Pricing sensitivity (mentioned in 8/12) 2. Onboarding friction (6/12) 3. Feature requests for API access (5/12)
You: "Join my 2pm Zoom call, then send me a summary with action items" AI: → schedule_meeting_event(meetingUrl, scheduledAt: "2026-04-25T14:00:00Z") Done. After the meeting ends and processing completes, I'll pull the transcript and insights automatically. [After the meeting] → get_media_insights(mediaId) → ask_ai_chat(mediaIds: [...], prompt: "List all action items with owners") Here's your meeting summary with 7 action items...
You: "Prepare a brief from all meetings in the last week" AI: → list_media(from: "2026-04-18", mediaType: "audio") → get_media_insights(mediaId) [for each of 5 meetings] Weekly Meeting Brief (Apr 18-25): - Engineering Standup: Deployed v2.3, 2 bugs triaged - Sales Review: Pipeline at $1.2M, 3 deals closing this week - Product Sync: Finalized Q2 roadmap, new hire starts Monday Consolidated Action Items: [12 items grouped by owner]
The MCP server and CLI handle token management automatically. If you're calling the REST API directly, here's the full auth flow:
curl -X POST https://api.speakai.co/v1/auth/accessToken \ -H "Content-Type: application/json" \ -H "x-speakai-key: YOUR_API_KEY"
{ "data": { "email": "you@example.com", "accessToken": "eyJhbG...", "refreshToken": "eyJhbG..." } }
Step 2 — Use the token on all subsequent requests:
Connect Speak AI to Claude or ChatGPT in 60 seconds
For researchers, revenue teams, meeting-heavy teams, and media workflows.
No Terminal. No npm. No JSON config files.
Installation guide at docs.speakai.co/mcp →
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.
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
- Openclaude.ai/settings/connectors
- ClickAdd custom connector
- Name itSpeak AIand pastehttps://api.speakai.co/v1/mcp, then clickAdd
- A permission popup asks you to log into Speak AI and clickAllow
- Done — Speak AI shows in your connector list with its tools ready to use. Open a new chat and ask about your recordings.
3. Add custom connector dialog— name and URL filled in.
5. Connected— Speak AI tools appear in your connector list.
Get a key atapp.speakai.co/developers/apikeys, then in step 2 also expandCustom headersand add:
- Header name:Authorization
- Header value:Bearer <your-speak-api-key>
1. Connect screen in ChatGPT— paste the connector URL and pick OAuth.
2. Confirm and continue— ChatGPT asks you to continue to Speak AI.
4. Connected— Speak AI now shows in your ChatGPT connector list.
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 checkSettings → 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).
Recommended — install from the official Claude Code plugin marketplace:
- Add the official marketplace (one-time):/plugin marketplace add claude-plugins-official
- Install the plugin:/plugin install speakai@claude-plugins-official
- Activate it:/reload-plugins
- Run thegetting-startedskill and paste your Speak AI API key. Generate one atapp.speakai.co/developers/apikeys.
If/plugin installdoesn't find Speak AI, refresh the local catalog with/plugin marketplace update claude-plugins-officialand retry.
Skip the plugin and add the connector directly:
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:
claude mcp add speakai --transport http --url https://api.speakai.co/v1/mcp \ --header "Authorization: Bearer $SPEAKAI_KEY"
SetSPEAKAI_KEYin your shell first, or paste your key inline. Generate a key atapp.speakai.co/developers/apikeys.
Use the manual stdio setup in the Developer reference at the bottom of this README.
Use the manual stdio setup in the Developer reference at the bottom of this README.
Speak AI is published as a skill on ClawHub for OpenClaw-compatible agents.
- Visit theSpeak AI skill page on ClawHub
- Follow the install instructions for your agent — e.g.clawhub install speakaifrom the ClawHub CLI
- Set yourSPEAK_API_KEYenvironment variable. Generate one atapp.speakai.co/developers/apikeys.
For developers calling the Responses API directly. Pass the bearer token in the tool config:
{ "tools": [ { "type": "mcp", "server_url": "https://api.speakai.co/v1/mcp", "authorization": "Bearer YOUR_SPEAK_API_KEY" } ] }
Get a key atapp.speakai.co/developers/apikeys.
When you clickAllowon 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 atapi.speakai.co/v1/oauth/connections, or rotating/revoking your API key atapp.speakai.co/developers/apikeys.
For questions about data handling, seespeakai.co/privacyor emailsuccess@speakai.co.
You shouldn't need to be technical to install this.If anything is confusing or doesn't work:
- Emailsuccess@speakai.co— we'll respond within 24 hours
- Book a demo with usand we'll set it up together
Speak AI ships 113 tools your AI assistant can call. You don't memorize them — Claude/ChatGPT pick the right ones based on what you ask. Examples by category:
Full tool catalog is in the developer reference below.
Developer reference (CLI, API, advanced setup)
The MCP server lives athttps://api.speakai.co/v1/mcpand supports two auth methods:
- OAuth 2.1 + Dynamic Client Registration— install by pasting the URL above into any MCP client and approving the consent popup. Discovery, DCR,/authorize+ consent,/token, and revocation endpoints are all available.
- Bearer token(your Speak AI API key —Authorization: Bearer <key>header). For clients that don't speak OAuth, plus the npm CLI and stdio mode.
Get a Speak AI API key atapp.speakai.co/developers/apikeys.
The@speakai/mcp-servernpm package provides:
- A CLI (speakai-mcp) for scripting and pipelines (30 commands).
- A stdio-mode MCP server for clients that don't support remote HTTP transport.
- An auto-setup wizard that detects installed MCP clients and configures them.
npm install -g @speakai/mcp-server speakai-mcp init
Add to~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or%APPDATA%\Claude\claude_desktop_config.json(Windows):
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
export SPEAK_API_KEY="your-api-key" claude mcp add speak-ai -- npx -y @speakai/mcp-server
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
{ "mcpServers": { "speak-ai": { "command": "npx", "args": ["-y", "@speakai/mcp-server"], "env": { "SPEAK_API_KEY": "your-api-key" } } } }
SPEAK_API_KEY=your-key npx @speakai/mcp-server
Resources provide direct data access without tool calls. Clients can read these URIs directly.
Pre-built workflow prompts that agents can invoke to run multi-step tasks.
Upload a recording and get a full analysis — transcript, insights, action items, and key takeaways.
Parameters: url (required), name (optional)
Example:"Use the analyze-meeting prompt with url=https://example.com/standup.mp3"
Search for themes, patterns, or topics across multiple recordings or your entire library.
Parameters: topic (required), folder (optional)
Example:"Use the research-across-media prompt with topic='customer churn reasons'"
Prepare a brief from recent meetings — pull transcripts, extract decisions, and summarize open items.
Parameters: days (optional, default: 7), folder (optional)
Example:"Use the meeting-brief prompt with days=14 to cover the last two weeks"
npm install -g @speakai/mcp-server speakai-mcp config set-key
- --json— output raw JSON (for scripting and piping)
- --help— show command-specific help
# Upload and wait for processing speakai-mcp upload https://example.com/interview.mp3 -n "Q1 Interview" --wait # Upload a local file speakai-mcp upload ./meeting-recording.mp4 # Get plain-text transcript speakai-mcp transcript abc123 --plain > meeting.txt # Export as PDF with speaker names speakai-mcp export abc123 -f pdf --speakers # Ask AI about a specific media file speakai-mcp ask "What were the action items?" -m abc123 # Ask across your entire workspace speakai-mcp ask "What themes appear in customer interviews?" # Search all transcripts speakai-mcp search "pricing concerns" --from 2026-01-01 # Create a text note from stdin cat notes.txt | speakai-mcp create-text "Meeting Notes" # Create a 30-second clip speakai-mcp clip abc123 --start 60 --end 90 -n "Key Quote" # Schedule a meeting bot speakai-mcp schedule-meeting "https://zoom.us/j/123456" -t "Weekly Standup" # List videos as JSON for scripting speakai-mcp ls --type video --json | jq '.mediaList[].name' # List media from the last week speakai-mcp ls --from 2026-04-18 --to 2026-04-25 # Move 3 files to a folder speakai-mcp move folder123 media1 media2 media3
You: "Upload and transcribe this recording: https://example.com/meeting.mp3" AI: I'll upload that for you and start processing. → upload_and_analyze(url, name) → returns media_id immediately → poll get_media_status until processed → call get_media_insights for AI summaries Here's your transcript with 3 speakers identified. Key insights: 5 action items, positive sentiment overall. Top topics: Q2 roadmap, hiring plan, budget review.
You: "What themes came up across all our customer interviews this month?" AI: Let me search your media library. → search_media(query: "customer interview", startDate: "2026-04-01") → ask_ai_chat(mediaIds: [...], prompt: "What are the recurring themes?") Across 12 interviews, the top themes were: 1. Pricing sensitivity (mentioned in 8/12) 2. Onboarding friction (6/12) 3. Feature requests for API access (5/12)
You: "Join my 2pm Zoom call, then send me a summary with action items" AI: → schedule_meeting_event(meetingUrl, scheduledAt: "2026-04-25T14:00:00Z") Done. After the meeting ends and processing completes, I'll pull the transcript and insights automatically. [After the meeting] → get_media_insights(mediaId) → ask_ai_chat(mediaIds: [...], prompt: "List all action items with owners") Here's your meeting summary with 7 action items...
You: "Prepare a brief from all meetings in the last week" AI: → list_media(from: "2026-04-18", mediaType: "audio") → get_media_insights(mediaId) [for each of 5 meetings] Weekly Meeting Brief (Apr 18-25): - Engineering Standup: Deployed v2.3, 2 bugs triaged - Sales Review: Pipeline at $1.2M, 3 deals closing this week - Product Sync: Finalized Q2 roadmap, new hire starts Monday Consolidated Action Items: [12 items grouped by owner]
The MCP server and CLI handle token management automatically. If you're calling the REST API directly, here's the full auth flow:
curl -X POST https://api.speakai.co/v1/auth/accessToken \ -H "Content-Type: application/json" \ -H "x-speakai-key: YOUR_API_KEY"
{ "data": { "email": "you@example.com", "accessToken": "eyJhbG...", "refreshToken": "eyJhbG..." } }
Step 2 — Use the token on all subsequent requests:
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
