Integration

Online Speech to Text Cloud integration

Online Speech to Text Cloud is a German-hosted transcription service. Transcribe an uploaded audio or video file in any of 100 languages or with automatic language detection, read the transcript with or without timestamps, get a download link for TXT, PDF, DOCX, HTML, SRT or VTT, and run an AI text task on a finished transcript: summarize, translate, identify speakers, clean up, extract key points, fix compliance or extract CSV. A transcript carries whatever is said in the recording, personal data included. Transcription uses the plan's monthly minutes and each text task one of the plan's monthly task actions; uploads and transcripts are deleted after 24 hours. API access needs a Premium or Business plan. Authentication is an API key (it starts with stt_live_) sent in the x-api-key header.

Connect Online Speech to Text Cloud How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Online Speech to Text Cloud.Built from the 3 Online Speech to Text Cloud tools below, on the connection you add once.

What you can do with Online Speech to Text Cloud

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Transcription job, 2 operations

get_transcription_jobGet transcription jobPOSTAgents: ask firstReads a transcription job: status (processing, finished or error), progress and, once finished, the transcript and a download link valid 6 hours. Pass task to read a text task's result. Not cached, so it can be polled.
transcribe_audioTranscribe audioPOSTAgents: ask firstUploads an audio or video file for transcription (uses the plan's monthly minutes) and returns the finished job: job_id, transcript with timestamps, detected_language. Waits for the job and returns the finished result; gives up after 10 minutes.

Transcript task, 1 operation

run_transcript_taskRun transcript taskPOSTAgents: ask firstStarts an AI text task on a finished transcription job and returns at once with status processing. Uses one of the plan's monthly task actions. Then poll get_transcription_job with the same job_id and task.

Use Online Speech to Text Cloud from Claude Code, Cursor or Codex

Connect Online Speech to Text Cloud in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Online Speech to Text Cloud 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 Online Speech to Text Cloud

Create your workspace
Sign up free. Nothing to install.
Connect Online Speech to Text Cloud once
Add your Online Speech to Text Cloud 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.