Skip to main content

Transcription MCP

In one line: Convert any recorded audio (a call, a voice note, an uploaded file) into a clean text transcript your agent can use.
CategoryAI & Media
AuthenticationPlatform-managed
Setup time~1 minute
DifficultyEasy
Best forTranscribing calls and audio for summaries, search, QA, and follow-ups

1. Overview

Transcription (speech-to-text) converts spoken audio into written text. Give it the URL of an audio file and it returns the words that were said, smart-formatted and ready to use. Once connected, your agent can transcribe recorded calls, voicemails, and uploaded audio, choose between speech providers (Deepgram or Azure), and target a specific language when you know it. The result is plain text you can summarize, search, score, or store. Connecting Transcription to UnleashX lets your voice and automation agents turn raw audio into structured insight — call summaries, sentiment, action items — without anyone listening back manually.

2. What you’ll need

Transcription is built into UnleashX. There are no third-party accounts (Deepgram/Azure) for you to create and no API keys for you to manage.
  • An active UnleashX account.
  • The Transcription feature enabled on your workspace/plan.
  • A publicly reachable URL to the audio file you want transcribed.
  • Permission to edit the agent (admin or editor role). Without it, ask a workspace admin to enable the feature.

3. Get your credentials

There are no credentials to create. Transcription is platform-managed — UnleashX provisions and rotates the underlying Deepgram and Azure Speech keys. You never handle a provider key.
If you are a workspace admin, the only optional platform-side choices are which provider and default model/language to use. UnleashX ships sensible defaults; most teams never change them.
Platform-managed settingPlain-English reason it exists
Provider (Deepgram / Azure)Lets UnleashX route audio to the speech engine that fits your needs.
Default model & languageSets transcription quality and the expected spoken language.
Provider API keysProvisioned and rotated by UnleashX so transcription “just works.”

4. Connect on UnleashX

1

Open your agent

Go to https://www.tryunleashx.com and open the agent that should transcribe audio.
2

Open Data Connectors

In the agent, click Data Connectors.
3

Find Transcription and add it

Locate Transcription and click Connect / Add. It’s platform-managed, so there’s no key to paste — it activates immediately.
4

Confirm it's connected

The Transcription tool should now show a Connected badge.

5. Available tools

01 transcription tools
ToolWhat it doesChanges data?
Transcribe AudioTranscribe audio from a URL using the Deepgram or Azure providerNo
Transcription is read-only — it reads an audio file and returns text. It does not alter or store the source recording.

6. Example usage

“Transcribe this call recording and give me a summary.” → Runs Transcribe Audio on the recording URL, then the agent summarizes the returned transcript. “Get the text of this Hindi voicemail.” → Runs Transcribe Audio with the language set to Hindi (hi-IN) so the transcript comes back accurately.

7. Permissions & data access

UnleashX can:
  • Download the audio file at the URL you provide.
  • Send it to the configured speech provider and return the transcript.
  • Temporarily process and convert the audio (e.g. to a compatible format).
UnleashX cannot:
  • Access audio you don’t explicitly pass to the tool.
  • Permanently store your recordings as part of the integration.
  • Record new audio on its own.
To disconnect: Open the agent → Data ConnectorsTranscriptionDisconnect. Access is revoked immediately.

8. Troubleshooting

ProblemWhat it meansHow to fix it
”url must be a valid http or https URL”The audio link is missing or malformedPass a full, public http(s) URL to the audio file
”Audio file too large”The file exceeds the 50 MB limitTrim or compress the recording, or split it
401 / credential errorThe platform-managed provider key is unavailablePlatform-side — contact cs@unleashx.ai
403 / feature not enabledTranscription isn’t enabled on your planAsk a workspace admin or contact support
Empty transcriptSilent audio, wrong language, or unsupported formatConfirm the file has speech and set the right language
For general connector issues, see /mcp/integrations.

9. Frequently asked questions

Is my audio stored? No. The file is downloaded only to produce the transcript and is not retained as part of the integration. Temporary working files are cleaned up. Do I need a Deepgram or Azure account? No. Transcription is platform-managed — UnleashX provides and rotates the provider keys. Which provider is used? Deepgram or Azure, depending on your workspace configuration. You can pass stt_provider_name to choose per request. Can multiple team members use it? Yes. Once enabled on the workspace, anyone with access to the agent can transcribe audio.

10. References