Skip to content
PipMCP

Integration · Company data

Connect Claude & ChatGPT to AssemblyAI

Give your AI a link to a recording and ask it to transcribe it with AssemblyAI. It can start transcripts with speaker labels, summaries or chapters, check when they are done, split them into sentences or paragraphs, export subtitles and find where a word was said. Your recordings turn into text you can work with in the chat.

Connect AssemblyAI free

Free plan, no credit card. Takes about a minute.

Try asking

  • “Transcribe this recording with speaker labels: https://example.com/meeting.mp3”

    The AI starts a transcript from the audio URL with speaker labels on. It runs in the background, and the AI checks back until it is done.

  • “Is yesterday's interview transcript finished yet?”

    It lists your recent transcripts and reads the status and text of the one you mean.

  • “Give me the interview as paragraphs with timestamps.”

    It fetches the completed transcript split into paragraphs, each with start and end time.

What your AI can do

Transcription

Start transcripts from an audio or video URL, with optional speaker labels, language detection, summaries, chapters and PII redaction.

Structured text

Read finished transcripts in full or split into sentences and paragraphs with timestamps and speakers.

Subtitles and search

Export subtitles as SRT or VTT and find where specific words or phrases occur.

  • “Export subtitles for this video as SRT.”

    It exports the completed transcript as SRT subtitles, ready to upload with the video.

  • “Where in the call did anyone mention pricing?”

    It searches the transcript for the word and returns each match with its timestamp.

  • “Delete the transcript of the test recording.”

    It permanently deletes the transcript's text and audio data. This cannot be undone.

8 tools for AssemblyAI

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

  • create_transcriptChanges dataStart transcribing an audio or video file from a public `audio_url`. Optional: speaker_labels, language_code or language_detection, summarization, auto_chapters, redact_pii. Transcription runs in the background; poll get_transcript with the returned ID.
  • delete_transcriptDeletesPermanently delete a transcript's text and audio data by `transcript_id`. This cannot be undone.
  • get_subtitlesExport a completed transcript as subtitles by `transcript_id` and `subtitle_format` (srt or vtt). Optional `chars_per_caption`.
  • get_transcriptGet one transcript by `transcript_id`: status, full text, words, and any speaker labels, summary or chapters that were requested. Poll this until status is completed.
  • list_transcript_paragraphsGet a completed transcript split into paragraphs, with start and end times, by `transcript_id`.
  • list_transcript_sentencesGet a completed transcript split into sentences, with start and end times and speaker for each, by `transcript_id`.
  • list_transcriptsList your transcripts, newest first, optionally filtered by `status` (queued, processing, completed, error) or `created_on` date. Use to find a transcript ID.
  • search_transcript_wordsFind where specific words or phrases occur in a completed transcript. Pass `transcript_id` and a list of `words`; returns matches with timestamps.

Set up in three steps

  1. 1

    Pick the app

    Create a free PipMCP account and choose AssemblyAI from the app list.

  2. 2

    Paste your key

    Paste your AssemblyAI API key. Sign in to the AssemblyAI dashboard and copy your key from the API Keys section, or create a new one there.

  3. 3

    Add the link to your AI

    You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:

    1. Click your name, then Settings › Connectors › Add custom connector.
    2. Paste your link as the Remote MCP server URL.
    3. Switch it on from the + menu in a chat.

Questions

What can the AI do in AssemblyAI?

It can start a transcript from a public audio or video URL, list your transcripts, read a transcript with its status and text, split it into sentences or paragraphs, export SRT or VTT subtitles and search it for words. It can also delete a transcript.

Does the AI see my AssemblyAI API key?

No. Your AssemblyAI API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with reading existing transcripts. Deleting a transcript is permanent and can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan, and you do not need a credit card to start. Paid plans are billed per completed task. You also need your own AssemblyAI account, so any usage AssemblyAI charges for is between you and AssemblyAI.

Can the AI transcribe a file on my computer?

Not directly. The AI starts a transcript from an audio or video URL, so the file needs to be reachable at a public link. Transcription runs in the background, and the AI checks the transcript until its status is completed.

Related integrations

Let your AI work in AssemblyAI today.

Start free. Your key stays encrypted, and you decide what the AI may do.

Connect AssemblyAI free

PipMCP is not affiliated with AssemblyAI. Product names are trademarks of their owners.