Voicenotes Official

This official skill from the Voicenotes team gives OpenClaw access to new APIs and the ability to search semantically, retrieve full transcripts, filter by t...

Security Scan

The skill's requirements, runtime instructions, and declared credential needs match its stated purpose (accessing Voicenotes via their API) and contain no unexplained requests or installs.

Purpose & Capability

The name/description describe Voicenotes API access (search, transcripts, create notes). The only required binary is curl and the only required env var is VOICENOTES_API_KEY — both are appropriate and expected for an HTTP-based integration.

Instruction Scope

SKILL.md contains curl examples and endpoints scoped to api.voicenotes.com and instructs how to set VOICENOTES_API_KEY. It does not instruct reading unrelated files, other env vars, or sending data to off-site endpoints beyond the Voicenotes API. The security/guardrail claims are statements in the doc, not enforceable checks.

Install Mechanism

No install spec or code files are present (instruction-only skill). This is low-risk: nothing is downloaded or written to disk by an installer.

Credentials

Only a single API key (VOICENOTES_API_KEY) is required and it is declared as the primary credential. That is proportional to the described functionality.

Persistence & Privilege

always is false and the skill does not request elevated platform presence or modify other skills. Note: disable-model-invocation is false (default), so the agent may call the skill autonomously when permitted — this is normal but worth awareness.

Assessment

This skill appears coherent and limited to calling the Voicenotes API using your VOICENOTES_API_KEY. Before installing, confirm the integration URL and that you obtained the API key from https://voicenotes.com (or your account settings). Treat the API key as sensitive: only provide a key with the minimum necessary scope, monitor usage, and be prepared to rotate/revoke it if you see unexpected calls. Remember the SKILL.md's security statements are documentation — the platform does not automatically enforce them, so avoid sharing keys you wouldn't want a tool to use to read or create notes. If the skill later includes an install script or code files, re-evaluate before permitting installation or granting credentials.

voicenotes

Use the Voicenotes skill to create, search and retrieve user’s notes.

Setup

1. Create an integration at https://voicenotes.com/app?open-claw=true#settings
2. Copy the API key
3. Configure it:

Webchat: Skills → Voicenotes → API Key in the sidebar

Terminal: Add to your OpenClaw config (~/.openclaw/config.yaml):

skills:
  voicenotes:
    env:
      VOICENOTES_API_KEY: "your_key_here"

Or export it directly:

export VOICENOTES_API_KEY="your_key_here"

The key is then available as $VOICENOTES_API_KEY environment variable.

API Basics

All requests need the Authorization header:

curl -X GET "https://api.voicenotes.com/api/integrations/open-claw/..." \
  -H "Authorization: $VOICENOTES_API_KEY"

Common Operations

Search query in users notes:

Query parameters:

• query (required): The search query string

curl -X GET "https://api.voicenotes.com/api/integrations/open-claw/search/semantic?query={search_query}" \
  -H "Authorization: $VOICENOTES_API_KEY"

Get multiple Voicenotes with filters (tags and date range):

Query parameters:

• tags (optional): array of valid tags
• date_range (optional): array with start and end date as UTC timestamps

curl -X POST "https://api.voicenotes.com/api/integrations/open-claw/recordings" \
  -H "Authorization: $VOICENOTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tags": ["tag1", "tag2"],
    "date_range": ["2026-01-01T00:00:00.000000Z", "2026-02-01T00:00:00.000000Z"]
  }'

If you want more context get the whole transcript:

curl "https://api.voicenotes.com/api/integrations/open-claw/recordings/{recording_uuid}" \
  -H "Authorization: $VOICENOTES_API_KEY" \

Create a text note in Voicenotes:

curl -X POST "https://api.voicenotes.com/api/integrations/open-claw/recordings/new" \
  -H "Authorization: $VOICENOTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "recording_type": 3,
    "transcript": "note content here",
    "device_info": "open-claw"
  }'

Response Structure

Semantic Search Response:

Returns an array of notes and note splits ordered by relevance:

[
  {
    "type": "note",
    "uuid": "NTHiJljf",
    "title": "Quick idea about project",
    "transcript": "Full transcript text with <br> for line breaks...",
    "tags": ["idea", "project"],
    "created_at": "2025-01-15T10:30:00.000000Z"
  },
  {
    "type": "note_split",
    "uuid": "8JzkhEGh",
    "title": "Long meeting notes",
    "transcript": "Relevant chunk from a larger note...",
    "tags": ["meeting"],
    "created_at": "2025-01-14T09:00:00.000000Z"
  },
  {
    "type": "import_split",
    "uuid": "xYz12345",
    "title": "filename.extension",
    "transcript": "Chunk from an imported note...",
    "tags": ["imported"],
    "created_at": "2025-01-10T14:00:00.000000Z"
  }
]

• type: "note" - Complete note matching the search
• type: "note_split" - Chunk from a larger note; use the uuid to fetch full transcript if needed
• type: "import_split" - Chunk from an imported note; title is the filename; cannot be fetched via /recordings/{uuid}
• transcript may contain HTML (<br>, <b>) for formatting

Get Recordings Response (with filters):

Returns paginated notes matching the filters:

{
  "data": [
    {
      "id": "bTZI5t12",
      "title": null,
      "transcript": "this is a sample note",
      "duration": 0,
      "recorded_at": "2026-02-06T10:07:45.000000Z",
      "created_at": "2026-02-06T10:07:45.000000Z",
      "recording_type": 3,
      "tags": []
    }
  ],
  "links": {
    "first": "https://api.voicenotes.com/api/integrations/open-claw/recordings?page=1",
    "last": null,
    "prev": null,
    "next": null
  },
  "meta": {
    "current_page": 1,
    "from": 1,
    "path": "https://api.voicenotes.com/api/integrations/open-claw/recordings",
    "per_page": 10,
    "to": 1
  }
}

Key fields:

• data - Array of recording objects
• links.next - URL for next page (null if no more pages)
• meta.per_page - Results per page (default 10)

Get Recording Response:

Returns full note details:

{
  "data": {
    "id": "NTHiJljf",
    "title": "Meeting Connectivity Check",
    "transcript": "Full transcript text...",
    "duration": 12101,
    "recorded_at": "2025-08-07T09:50:14.000000Z",
    "created_at": "2025-08-07T09:50:14.000000Z",
    "recording_type": 2,
    "tags": ["meeting"],
    "subnotes": [],
    "attachments": []
  }
}

Key fields:

• id - Note UUID
• transcript - Full text (meetings include [HH:MM:SS] Speaker N: timestamps)
• duration - Length in milliseconds
• recording_type - 1=voice note, 2=voice meeting, 3=text note
• tags - Array of tag objects with name field

Create Note Response:

{
  "message": "Recording audio uploaded successfully!",
  "recording": {
    "id": "bPI3RcUP",
    "recording_id": "bPI3RcUP",
    "title": null,
    "transcript": "Sample note",
    "recording_type": 3,
    "created_at": "2026-02-04T08:51:29.000000Z",
    "tags": []
  }
}

Key fields:

• message - Success confirmation
• recording.id - New note UUID
• recording.transcript - The note content

Notes

• Note IDs are UUIDs
• Rate limit: ~3 requests/second average

Security & Guardrails

• Only accesses api.voicenotes.com endpoints
• No credential exfiltration or external data storage
• No telemetry or analytics
• No automatic code execution or file overwrites
• Read/write limited to user's own Voicenotes data via authenticated API

Input Sanitization

When constructing API requests, the agent MUST sanitize all user-provided inputs:

• Search queries: URL-encode the query parameter using --data-urlencode instead of string interpolation
• Recording UUIDs: Validate format (alphanumeric, 8 characters) before use; reject any input containing shell metacharacters (;, |, &, $, `, \)
• JSON body fields: Use proper JSON encoding; never concatenate raw user input into JSON strings

Safe example for search:

curl -G "https://api.voicenotes.com/api/integrations/open-claw/search/semantic" \
  --data-urlencode "query=user search term here" \
  -H "Authorization: $VOICENOTES_API_KEY"

UUID validation pattern: /^[a-zA-Z0-9]{8}$/