Install
openclaw skills install @julianpscheid/hedyAccess and manage Hedy meeting data: sessions, transcripts, highlights, todos, topics, contexts, vocabulary, and webhooks via the Hedy REST API.
openclaw skills install @julianpscheid/hedyAccess a user's Hedy meeting data through the Hedy REST API. Read sessions with transcripts and highlights. Manage todos, topics, session contexts, custom vocabulary, and webhooks.
Hedy is an AI-powered meeting coach that provides real-time speech transcription and AI-powered conversation analysis. This skill lets you query the user's meeting history, search for specific sessions, retrieve structured meeting outputs, and manage organizational features like topics and webhooks.
Generate an API key inside the Hedy app under Settings > API. Keys start with hedy_live_.
Add the following to ~/.openclaw/openclaw.json:
{
"skills": {
"entries": {
"hedy": {
"enabled": true,
"apiKey": "hedy_live_YOUR_KEY_HERE",
"config": {
"region": "us"
}
}
}
}
}
Set "region" to "eu" if your Hedy account uses EU data residency. Default is "us".
If you run OpenClaw in a Docker sandbox, apiKey and env values from openclaw.json are injected into the host process only. Add the key to your sandbox environment separately:
{
"agents": {
"defaults": {
"sandbox": {
"docker": {
"env": {
"HEDY_API_KEY": "hedy_live_YOUR_KEY_HERE"
}
}
}
}
}
}
Start a new session so the skill is picked up.
Determine the base URL from the configured region:
| Region | Base URL |
|---|---|
us (default) | https://api.hedy.bot |
eu | https://eu-api.hedy.bot |
If no region is configured, default to us.
All endpoints below use {BASE_URL} as a placeholder. Replace it with the resolved URL.
Every request requires:
Authorization: Bearer {HEDY_API_KEY}
The API key is injected via the HEDY_API_KEY environment variable. Never display, log, or include the API key in output shown to the user.
All endpoints return JSON. Response shapes vary by endpoint (documented individually below). Error responses always use:
{
"success": false,
"error": { "code": "error_code", "message": "Human-readable message" }
}
The live OpenAPI schema at {BASE_URL}/docs is authoritative. Check it before using an operation or field not documented here.
Returns the authenticated user's profile. Response is a bare JSON object (no wrapper).
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/me" | jq
Response:
{
"id": "uid_123",
"email": "user@example.com",
"name": "John Doe"
}
List recent meeting sessions. Only cloud-synced sessions are returned. Response is wrapped in { success, data, pagination }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/sessions?limit=20" | jq
Query parameters:
limit (int, 1-100, default 50): Number of sessions to returnafter (string, optional): Session ID from the previous response's pagination.nextTo retrieve additional sessions, repeat the request with after={pagination.next} while pagination.hasMore is true.
Response:
{
"success": true,
"data": [
{
"sessionId": "sess_123",
"title": "Weekly Sync",
"startTime": "2026-03-15T14:30:00Z",
"duration": 45,
"session_type": "business_meetings",
"topic": { "id": "topic_1", "name": "Team Meetings" }
}
],
"pagination": { "hasMore": true, "next": "sess_123", "total": 42 }
}
Full session detail including transcript, AI outputs, highlights, and todos. Response is a bare JSON object (no wrapper).
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/sessions/{sessionId}" | jq
Response:
{
"sessionId": "sess_123",
"title": "Weekly Sync",
"startTime": "2026-03-15T14:30:00Z",
"endTime": "2026-03-15T15:15:00Z",
"duration": 45,
"session_type": "business_meetings",
"transcript": "full meeting transcript text",
"cleaned_transcript": "AI-cleaned version or null",
"cleaned_at": "2026-03-15T16:00:00Z",
"conversations": "Q&A structured format",
"meeting_minutes": "formatted minutes",
"recap": "brief summary",
"session_notes": "[{\"insert\":\"Key takeaway\\n\"}]",
"highlights": [],
"user_todos": [],
"topic": { "id": "topic_1", "name": "Team Meetings" }
}
session_notes is Parchment Delta JSON encoded as a string. Transcript and current structured cleaned-transcript speaker labels resolve from the Session's current speaker names, so they can change after a speaker rename.
Highlights (key quotes) from a specific session.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/sessions/{sessionId}/highlights" | jq
Todos from a specific session.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/sessions/{sessionId}/todos" | jq
A specific todo item.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/sessions/{sessionId}/todos/{todoId}" | jq
Update a stable-ID todo's completion state, due date, or both. An empty dueDate clears the due date.
curl -s -X PATCH -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"completed": true, "dueDate": "Friday"}' \
"{BASE_URL}/sessions/{sessionId}/todos/{todoId}" | jq
The body must contain at least one of:
completed (boolean)dueDate (string, max 200 chars)The response is wrapped in { success, data }, where data is the updated todo.
List all highlights across all sessions, sorted by timestamp (newest first). Response is wrapped in { success, data, pagination }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/highlights?limit=20" | jq
Query parameters:
limit (int, 1-100, default 50)after (string, optional): Highlight ID from the previous response's pagination.nextTo retrieve additional highlights, repeat the request with after={pagination.next} while pagination.hasMore is true.
Response:
{
"success": true,
"data": [
{
"highlightId": "high_123",
"sessionId": "sess_456",
"timestamp": "2026-03-15T14:35:00Z",
"title": "Key Decision"
}
],
"pagination": { "hasMore": true, "next": "high_123", "total": 15 }
}
Full highlight detail. Response is a bare JSON object (no wrapper).
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/highlights/{highlightId}" | jq
Response:
{
"highlightId": "high_123",
"sessionId": "sess_456",
"timestamp": "2026-03-15T14:35:00Z",
"timeIndex": 300000,
"title": "Key Decision on Mobile App",
"rawQuote": "yeah I think we should prioritize the mobile app",
"cleanedQuote": "We should prioritize the mobile app",
"mainIdea": "Team agreed to prioritize mobile app development",
"aiInsight": "Strategic prioritization of mobile platform"
}
All todos across all sessions. Returns a flat array (no pagination wrapper).
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/todos" | jq
Response (array of):
{
"id": "uuid-1234",
"text": "Follow up with John",
"dueDate": "Tomorrow",
"sessionId": "sess_123",
"completed": false,
"topic": { "id": "topic_1", "name": "Team Meetings" }
}
List all topics (conversation groupings), sorted by last update. Response is wrapped in { success, data }. No pagination.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/topics" | jq
Response data (array of):
{
"id": "topic_123",
"name": "Project Alpha",
"description": "All about Project Alpha",
"color": "#FF5733",
"iconName": "59475",
"topicContext": "Custom instructions for this topic",
"topicContextUpdatedAt": "2026-03-15T16:00:00Z",
"sessionCount": 12,
"lastSessionDate": "2026-03-15T14:30:00Z",
"dominantSessionType": "group_brainstorm",
"overview": { "summary": "..." },
"overviewUpdatedAt": "2026-03-15T16:00:00Z",
"createdAt": "2026-02-01T10:00:00Z",
"updatedAt": "2026-03-15T16:00:00Z"
}
Fields like overview, overviewUpdatedAt, topicContext, and dominantSessionType may be null or absent if not yet generated.
Full topic detail including overview and insights. Response is wrapped in { success, data }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/topics/{topicId}" | jq
Sessions grouped under a topic. This endpoint uses its own startAfter cursor.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/topics/{topicId}/sessions?limit=20" | jq
Query parameters:
limit (int, 1-100, default 50)startAfter (string): Session ID cursor for next page (from data.pagination.nextCursor)Response:
{
"success": true,
"data": {
"sessions": [
{
"sessionId": "sess_123",
"title": "Q1 Planning",
"startTime": "2026-03-15T14:30:00Z",
"duration": 45,
"session_type": "business_meetings",
"topicInfo": { "id": "topic_123", "name": "Project Alpha" }
}
],
"pagination": {
"count": 20,
"hasMore": true,
"nextCursor": "sess_456"
}
}
}
To paginate, pass ?startAfter={data.pagination.nextCursor} until hasMore is false. This endpoint uses startAfter; the top-level Session and Highlight lists use after.
List session contexts (pre-meeting preparation notes), sorted by most recently updated. Response is wrapped in { success, data }. No pagination.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/contexts" | jq
Response data (array of):
{
"id": "ctx_abc123",
"title": "Sales Call Context",
"content": "Focus on customer pain points...",
"isDefault": true,
"createdAt": "2026-02-01T10:00:00Z",
"updatedAt": "2026-03-15T16:00:00Z"
}
A specific session context. Response is wrapped in { success, data }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/contexts/{contextId}" | jq
Return the complete custom vocabulary and whether matching is enabled. Response is wrapped in { success, data }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/vocabulary" | jq
Response data:
{
"terms": ["Hedy", "Portkey"],
"enabled": true
}
Replace the complete custom vocabulary list. Terms omitted from the request are removed; omit enabled to preserve its stored value.
curl -s -X PUT -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"terms": ["Hedy", "Portkey"], "enabled": true}' \
"{BASE_URL}/vocabulary" | jq
terms is required: at most 100 unique terms, 2-50 chars each, compared case-insensitively.enabled is an optional boolean.Create a new topic. Response is wrapped in { success, data }.
curl -s -X POST -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"name": "Project Alpha", "description": "All about Project Alpha", "color": "#FF5733"}' \
"{BASE_URL}/topics" | jq
Request body:
name (string, required): 1-100 charsdescription (string, optional): 0-500 charscolor (string, optional): Hex format RRGGBB, with or without #iconName (string, optional): Decimal or 0x hex icon codepoint; names are accepted but render as the default folder icontopicContext (string, optional): Custom instructions, 0-20,000 charsdominantSessionType (string or null, optional): Built-in Session type used to seed new Sessions under this TopicReturns HTTP 201 with the created topic object.
Update an existing topic. Response is wrapped in { success, data }.
curl -s -X PATCH -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"description": "Updated description"}' \
"{BASE_URL}/topics/{topicId}" | jq
Request body (all fields optional):
name (string): 1-100 charsdescription (string): 0-500 charscolor (string): Hex format RRGGBB, with or without #iconName (string): Decimal or 0x hex icon codepointtopicContext (string or null): Set to null to cleardominantSessionType (string or null): Seed new Sessions with a built-in Session type, or clear itValid dominantSessionType values: business_meetings, lecture_class, coaching_mentoring, recruitment_call, job_interview_candidate, negotiation, sales_meeting, journalism, spiritual_teaching, solo_brainstorm, group_brainstorm, personal_conversation, medical_consultation.
Returns HTTP 200 with the updated topic object.
Delete a topic. Sessions under this topic are unlinked (topicId set to null) but not deleted.
curl -s -X DELETE -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/topics/{topicId}" | jq
Returns HTTP 200:
{
"success": true,
"message": "Topic deleted"
}
Warning: Deletion is not fully atomic for large topics. The backend unlinks up to 4,000 sessions in batches. If a topic has more than 4,000 sessions, the request returns 400 deletion_limit_exceeded after partially unlinking sessions, and the topic is left in a deletion_failed state. If this happens, inform the user that manual cleanup may be needed in the Hedy app. A 409 deletion_in_progress error means another delete is already running for this topic.
Create a new session context. Response is wrapped in { success, data }.
curl -s -X POST -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"title": "Sales Call Context", "content": "Focus on customer pain points..."}' \
"{BASE_URL}/contexts" | jq
Request body:
title (string, required): 1-200 charscontent (string, optional): 0-20,000 charsisDefault (boolean, optional): If true, clears default from all other contextsReturns HTTP 201 with the created context object.
Note: Free tier users are limited to 1 session context. Additional contexts require a Pro subscription.
Update an existing session context. Response is wrapped in { success, data }.
curl -s -X PATCH -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"title": "Updated title", "isDefault": true}' \
"{BASE_URL}/contexts/{contextId}" | jq
Request body (all fields optional):
title (string): 1-200 charscontent (string): 0-20,000 charsisDefault (boolean): If true, clears default from all other contextsReturns HTTP 200 with the updated context object.
Delete a session context. If the deleted context was the default, the most recently updated remaining context is promoted to default.
curl -s -X DELETE -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/contexts/{contextId}" | jq
Returns HTTP 200:
{
"success": true,
"message": "Session context deleted"
}
List all configured webhooks. Response is wrapped in { success, data }.
curl -s -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/webhooks" | jq
Response data (array of):
{
"id": "wh_123",
"url": "https://api.example.com/hedy-webhook",
"events": ["session.ended", "highlight.created"],
"createdAt": "2026-02-01T10:00:00Z",
"updatedAt": "2026-02-01T10:00:00Z"
}
List responses never include signingSecret.
Create a webhook. Rate limited to 5 per minute. Maximum 50 webhooks per user. Requires HTTPS URL in production.
curl -s -X POST -H "Authorization: Bearer $HEDY_API_KEY" -H "Content-Type: application/json" \
-d '{"url": "https://api.example.com/hedy-webhook", "events": ["session.ended", "highlight.created"]}' \
"{BASE_URL}/webhooks" | jq
Request body:
url (string, required): Valid HTTPS URLevent (string) or events (string array): At least one required. Valid event types:
session.created - New session startedsession.ended - Session finished processingsession.exported - User manually exported sessionhighlight.created - New highlight generatedtodo.exported - Todo marked for exportsuggestion.created - Automatic feedback suggestion displayed during a live SessionReturns HTTP 200 with the created webhook object. Its signingSecret is returned only in this creation response; preserve it securely because subsequent GET requests omit it.
Delivered webhook bodies are flat: event fields sit beside the top-level event, with no nested data object and no top-level delivery timestamp. Session webhook fields use camelCase such as sessionType, topicId, and topicName, while REST Session responses use session_type and a nested topic. Current session.ended and session.exported payloads can include session_notes, structured_conversations, and Topic fields; older Hedy clients may emit reduced payloads.
Delete a webhook.
curl -s -X DELETE -H "Authorization: Bearer $HEDY_API_KEY" "{BASE_URL}/webhooks/{webhookId}" | jq
Returns HTTP 200:
{
"success": true,
"data": {
"message": "Webhook deleted successfully"
}
}
GET /sessions and GET /highlights support cursor pagination with limit and after. Use the previous response's pagination.next as after until pagination.hasMore is false.
GET /topics/{topicId}/sessions uses a separate startAfter cursor and returns it as data.pagination.nextCursor.
GET /todos, GET /topics, GET /contexts, and GET /vocabulary return their complete collections without cursor pagination.
| HTTP Status | Error Code | Meaning | Action |
|---|---|---|---|
| 400 | validation_error | Request body failed validation | Show the error message; check field constraints |
| 400 | bad_request | Todo update body is missing or invalid | Send completed, dueDate, or both with the documented types |
| 400 | invalid_cursor | Pagination cursor is unknown or ineligible | Restart from the first page rather than retrying the cursor |
| 400 | invalid_page_size | limit is outside 1-100 | Use a valid page size |
| 400 | invalid_webhook_url | Webhook URL is invalid | Ask user to provide a valid HTTPS URL |
| 400 | missing_event | Neither event nor events provided | Ask user which events to subscribe to |
| 400 | invalid_event | Single event type is invalid | Show the list of valid events |
| 400 | invalid_events | One or more event types invalid | Show the list of valid events |
| 400 | webhook_limit_exceeded | User has 50 webhooks already | Suggest deleting unused webhooks first |
| 400 | deletion_limit_exceeded | Topic has too many sessions (>4,000) for full cleanup | Inform user; partial unlink occurred, manual cleanup needed |
| 401 | missing_api_key | Authorization header missing | Check that HEDY_API_KEY is set |
| 401 | invalid_api_key | Key not found or wrong format | Ask user to verify their API key in Hedy app settings |
| 403 | tier_limit_exceeded | Feature requires Hedy Pro subscription | Inform user this feature requires a Pro plan |
| 404 | session_not_found | Session ID does not exist | Inform user; suggest listing sessions first |
| 404 | highlight_not_found | Highlight ID does not exist | Inform user |
| 404 | not_found | Topic or context does not exist | Inform user; suggest listing topics or contexts first |
| 404 | todo_not_found | Todo ID does not exist | Inform user |
| 404 | webhook_not_found | Webhook ID does not exist | Inform user; suggest listing webhooks first |
| 409 | deletion_in_progress | Topic deletion already running | Wait and retry later |
| 429 | rate_limit_exceeded | Too many requests (200/min global, 5/min for webhooks) | Wait 30 seconds before retrying. Do NOT retry immediately. |
| 500 | internal_error | Server error | Inform user and suggest trying again later |
For user-actionable errors (401, 403, 404), show the error.message from the response. For 429 and 500 errors, show a friendly summary instead (e.g., "The server is busy, please try again in a moment") since raw server messages may contain technical details. Never retry more than once on 429 or 500 errors.
~/.openclaw/openclaw.json."Show me my recent meetings" -> GET /sessions with limit=10, display as a table with title, date, duration, and topic.
"What were the key takeaways from my last meeting?" -> GET /sessions with limit=1 to find the most recent session, then GET /sessions/{id} for full detail. Present the recap and highlights.
"Do I have any open todos?" -> GET /todos, filter where completed is false, present as a checklist.
"Mark the follow-up todo complete"
-> GET /todos to resolve its Session and todo IDs, confirm the exact todo, then PATCH /sessions/{sessionId}/todos/{todoId} with {"completed": true}.
"Show me everything about Project Alpha" -> GET /topics to find the topic by name, then GET /topics/{id}/sessions to list all sessions under it.
"What did we discuss last Tuesday?" -> GET /sessions, scan startTime fields for the matching date, then GET /sessions/{id} for that session's detail.
"Show my session contexts" -> GET /contexts, present as a list with title and whether it's the default.
"Add Acme to my vocabulary" -> GET /vocabulary, append "Acme" without dropping the existing terms, show the complete replacement list, confirm, then PUT /vocabulary.
"Create a topic called Client Calls with a blue color" -> Confirm with user, then POST /topics with name "Client Calls" and color "#4A90D9".
"Delete the Project Alpha topic" -> GET /topics to find the ID, confirm with user showing the topic name and session count, then DELETE /topics/{id}.
"Set up a webhook for new highlights" -> Confirm the URL with user, then POST /webhooks with events ["highlight.created"].
"Create a context for investor meetings" -> Confirm with user, then POST /contexts with title "Investor Meetings" and relevant content.