Connect OpenClaw to Vocal Video
Set up in minutes
Choose where it runs
On your computer through your own OpenClaw, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Vocal Video
A preset of real Vocal Video operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Vocal Video
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your OpenClaw first calls in. OpenClaw probes the server while adding it, so this lights up during openclaw mcp add.
Run this in your terminal
<your-link> is your personal server URL — setup mints it for you.
Tools OpenClaw gets
Vocal Video
25 toolsRead workspace totals, usage meters and allowances. The publish, video-request and AI-credit meters are separate.
Find workspace video collectors. Results are a ranked shortlist; when truncated, narrow the filters rather than treating matched as a workspace total.
Read a collector, its ordered prompts, copy and settings.
Create a video request campaign, optionally with AI-generated prompts. New collectors are active immediately; AI generation spends credits.
Change selected collector copy and settings. Only supplied fields are sent; explicit null clears release, reward or template overrides.
Activate a collector or pause it so its link stops accepting submissions.
Preview invitation recipients with confirm=false. After confirming the preview, run again with the same recipients/message, confirm=true and the returned confirmation_token. Sending emails spends one video-request credit per recipient.
Find video/audio responses using transcript and respondent filters. Retains locked and pending-indexing indicators; pending indexing does not mean the workspace is empty.
Read a selected video/audio response and its footage details.
Mark a response as a workspace favorite.
Remove a response from workspace favorites.
Find workspace galleries. Results are a shortlist; narrow filters when truncated.
Read gallery details and item slot IDs.
Create a gallery with optional published storyboards and uploaded clips. Unpublished storyboards and response clips are rejected by Vocal Video.
Add one or several published videos to a gallery in the supplied order.
Remove an item from a gallery by slot ID, or by storyboard/clip ID. Slot ID from get_gallery is preferred.
Get a gallery sharing URL without changing its visibility.
Get a gallery embed snippet without changing its visibility.
Find workspace videos by content, publication and visibility. Shortlist results are not workspace totals.
Read the lighter video metadata and design summary without the scene list.
Read a selected video and its scenes, or request the lighter summary.
Change public video title/description and the internal workspace title.
Set video visibility to public and searchable, unlisted link access, or private workspace access.
Get a video sharing URL without changing its visibility.
Get video embed HTML with optional layout, playback and display settings.
About OpenClaw
Frequently asked questions
More ways to connect
More tools for OpenClaw
Use Vocal Video with other agents
Open your OpenClaw agent in one click.
NoClick runs OpenClaw for you with Vocal Video wired in as tools. Connect your account and run.