Speak AI
@speakai
About Speak AI
Official MCP server for Speak AI, transcribe meetings, analyze media, extract insights, and search across your entire audio/video library. 81 tools, 5 resources, 3 prompts. Upload recordings, get AI-powered transcripts and summaries, ask questions across files, create clips, sche
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"speak-ai": {
"command": "npx",
"args": [
"-y",
"@speakai/mcp-server"
],
"env": {
"SPEAK_API_KEY": "your-api-key"
}
}
}
}Tools
59Get a pre-signed S3 URL for direct media file upload. Use this before uploading a file directly to Speak AI storage.
Upload a media file to Speak AI by providing a publicly accessible URL. Speak AI will fetch and process the file asynchronously.
List all media files in the workspace with optional filtering, pagination, and sorting.
Retrieve AI-generated insights for a media file, including topics, sentiment, action items, and summaries.
Retrieve the full transcript for a media file, including speaker labels and timestamps.
Update or rename speaker labels in a media transcript.
Check the processing status of a media file (e.g. pending, transcribing, completed, failed).
Update metadata fields (name, description, tags, status) for an existing media file.
Permanently delete a media file and all associated transcripts and insights.
Create a new text note in Speak AI for analysis. The content will be analyzed for insights, topics, and sentiment.
Retrieve AI-generated insights for a text note, including topics, sentiment, summaries, and action items.
Trigger a re-analysis of an existing text note to regenerate insights with the latest AI models.
Update an existing text note's name, content, or metadata. Updating text content will trigger re-analysis.
Export a media file's transcript or insights in various formats (pdf, docx, srt, vtt, txt, csv, md).
Export multiple media files at once, optionally merged into a single file.
Retrieve all saved views across all folders.
Retrieve all saved views for a specific folder.
Create a new saved view for a folder with custom filters and display settings.
Update an existing saved view's name, filters, or display settings.
Duplicate an existing folder view.
List all folders in the workspace with pagination and sorting.
Get detailed information about a specific folder including its contents.
Create a new folder in the workspace.
Duplicate an existing folder and all of its contents.
Update a folder's name or other properties.
Permanently delete a folder. Media within the folder will be moved, not deleted.
Check whether a recorder/survey is active and accepting submissions.
Create a new recorder or survey for collecting audio/video submissions.
List all recorders/surveys in the workspace.
Duplicate an existing recorder including all its settings and questions.
Get detailed information about a specific recorder including its settings and questions.
List all submissions/recordings collected by a specific recorder.
Generate a shareable public URL for a recorder/survey.
Update configuration settings for a recorder (branding, permissions, etc.).
Update the survey questions for a recorder.
Permanently delete a recorder/survey. Existing recordings are preserved.
Create an embeddable player/transcript widget for a media file.
Update settings for an existing embed widget.
Check if an embed exists for a media file and retrieve its configuration.
Get the iframe URL for embedding a media player/transcript on a webpage.
List all available Magic Prompt templates for AI-powered questions about your media.
Ask an AI-powered question about a specific media file using Speak AI's Magic Prompt.
List scheduled or completed meeting assistant events with filtering and pagination.
Schedule the Speak AI meeting assistant to join and record an upcoming meeting.
Remove the Speak AI assistant from an active or scheduled meeting.
Cancel and delete a scheduled meeting assistant event.
List all custom fields defined in the workspace.
Create a new custom field for categorizing and tagging media.
Update multiple custom fields in a single batch operation.
Update a specific custom field by ID.
List all automation rules configured in the workspace.
Get detailed information about a specific automation rule.
Create a new automation rule for automatic media processing workflows.
Update an existing automation rule's configuration.
Enable or disable an automation rule.
Create a new webhook to receive real-time notifications when events occur in Speak AI.
List all configured webhooks in the workspace.
Update an existing webhook's URL or subscribed events.
Delete a webhook and stop receiving notifications at its endpoint.
Overview
What is Speak AI?
Speak AI is an MCP (Model Context Protocol) server and CLI that connects AI assistants like Claude, Cursor, and Windsurf to a Speak AI workspace. It provides 83 tools, 5 resources, and 3 prompts for transcribing, analyzing, searching, and managing media at scale.
How to use Speak AI?
Install globally via npm install -g @speakai/mcp-server, then run speakai-mcp init for auto-setup that detects and configures supported MCP clients. Alternatively, manually add the server configuration to each client using your Speak AI API key, set via the SPEAK_API_KEY environment variable.
Key features of Speak AI
- 83 MCP tools for media, AI chat, folders, and automations
- 5 resources for direct data access without tool calls
- 3 pre-built workflow prompts for multi-step tasks
- 28 CLI commands for scripting and automation
- Transcribe, analyze, search, and manage media at scale
Use cases of Speak AI
- Automate meeting transcription and AI analysis from uploaded recordings
- Search across transcripts, insights, and metadata for themes or patterns
- Create highlight clips from time ranges across media files
- Schedule an AI assistant to join and transcribe live meetings
- Manage media folders, exports, custom fields, and webhooks programmatically
FAQ from Speak AI
What API key is needed?
You need a Speak AI API key, obtainable from the Speak AI app at https://app.speakai.co/developers/apikeys.
How do I install the Speak AI MCP server?
Install globally with npm install -g @speakai/mcp-server, then run speakai-mcp init for auto-configuration. You can also run it on the fly with npx @speakai/mcp-server.
Which MCP clients are supported?
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, and any MCP client that supports STDIO transport. Each has specific configuration instructions in the README.
What environment variables are required?
SPEAK_API_KEY is required. Optionally, SPEAK_ACCESS_TOKEN (auto-managed) and SPEAK_BASE_URL (default https://api.speakai.co) can be set.
How many tools, resources, and prompts does it offer?
The server provides 83 MCP tools, 5 MCP resources, 3 MCP prompts, and 28 CLI commands.
More Media & Design MCP servers
YouTube MCP Server
ZubeidHendricksMCP Server for YouTube API, enabling video management, Shorts creation, and advanced analytics
Image-Gen-Server
fengin一个能与Cursor集成的图片生成mcp server工具，实现调用即梦逆向接口
Spotify MCP
varunnealMCP to connect your LLM with Spotify.
MCP Figma to React Converter
StudentOfJSMCP server for converting Figma designs to React components
RustChain MCP
ScottcjnMCP server for RustChain blockchain and BoTTube video platform — AI agent tools for earning RTC tokens. Built on createkr's RustChain SDK.
Comments