Integration

Temi integration

Temi (by Rev) turns audio and video into text with machine speech recognition. Submit the URL of a recording (including YouTube, Vimeo, Dropbox or Facebook links) and wait for the finished job, read its transcript as JSON with speakers and per-word timestamps, and list past jobs with their status and editor links. Uploading a media file directly (multipart) is not exposed, so pass a URL; deleting a job, minting a shareable editor link and reading the account balance are left to the Temi website. Temi bills $0.25 per minute of media, rounded up to the minute, from a prepaid balance. Authentication is an API key generated on the Temi developer page, sent as Authorization: Bearer <key>.

Connect Temi How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Temi.Built from the 3 Temi tools below, on the connection you add once.

What you can do with Temi

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Job, 1 operation

list_jobsList jobsGETLists the account's transcription jobs, latest first. Page through older jobs by passing the id of the last job received as starting_after.

Transcript, 1 operation

get_transcriptGet transcriptGETReturns the transcript of a transcribed job as JSON: the speakers, and the monologues with each word or tag and its start and end time in seconds.

Transcription, 1 operation

transcribe_mediaTranscribe mediaPOSTSubmits the URL of an audio or video file (YouTube, Vimeo, Dropbox and Facebook links work) for machine transcription. Read the text afterwards with get_transcript. Waits for the job and returns the finished result; gives up after 10 minutes.

Use Temi from Claude Code, Cursor or Codex

Connect Temi in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Temi operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Temi

Create your workspace
Sign up free. Nothing to install.
Connect Temi once
Add your Temi connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.