> ## Documentation Index
> Fetch the complete documentation index at: https://docs.atako.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AssemblyAI

> Connect AssemblyAI to your Atako agents — 7 read and 1 write actions.

Let your agents transcribe audio and video from public URLs with AssemblyAI (speaker labels, language detection, key phrases, entities, topics, sentiment, PII redaction), then read transcripts, sentences, paragraphs, subtitles and word matches.

## Connection

* **Authentication**: API key.
* **Required settings**:
  * **Region** — "api" for the default US endpoint, or "api.eu" for EU data residency (api.eu.assemblyai.com).

<Note>
  Sign in to the AssemblyAI dashboard (assemblyai.com/dashboard) → in the sidebar, Workspace → Manage → API Keys → Create New API Key. Enter a descriptive name, click Create and copy the key. Keys have no scopes: a key gives access to its project's transcripts. For EU data residency, set the region to "api.eu".

  See [AssemblyAI's documentation](https://www.assemblyai.com/dashboard/home).
</Note>

## Read actions (7)

| Action | Description |
| - | - |
| `get_redacted_audio` | Get the status and download URL of the PII-redacted audio copy of a transcript created with redact\_pii\_audio true. The URL is temporary (about 24 hours). |
| `get_subtitles` | Export a completed transcript as subtitles. Arguments: transcript\_id (string), subtitle\_format ("srt" or "vtt"), chars\_per\_caption (optional integer — maximum characters per caption). Returns the subtitle file as plain text. |
| `get_transcript` | Get a transcript by id: status ("queued", "processing", "completed", "error"), error message, full text, words, utterances (with speaker\_labels), detected language, and the results of the models enabled at creation — key phrases (auto\_highlights\_result), entities, topics (iab\_categories\_result), sentiment\_analysis\_results. Find ids with list\_transcripts. |
| `get_transcript_paragraphs` | Get a completed transcript split into paragraphs, each with its text, start/end timestamps (ms), confidence and words. |
| `get_transcript_sentences` | Get a completed transcript split into sentences, each with its text, start/end timestamps (ms), confidence, words and speaker. |
| `list_transcripts` | List the transcripts of the key's project, newest first. Optional filters: limit (1-200, default 10), status ("queued", "processing", "completed", "error"), created\_on (YYYY-MM-DD), before\_id / after\_id (transcript ids, for pagination — page\_details.prev\_url points to older transcripts), throttled\_only (boolean). Each item gives id, status, created, completed and audio\_url. |
| `search_transcript_words` | Search a completed transcript for words or phrases. Arguments: transcript\_id (string), words (array of strings, at least one). Returns the total count and, for each match, the text, count, timestamps and word indexes. |

## Write actions (1)

| Action | Description |
| - | - |
| `create_transcript` | Queue the transcription of an audio or video file reachable at a public URL (no file upload). Returns the transcript object with its id and status "queued"; poll get\_transcript until status is "completed" or "error". Arguments: audio\_url (string, required — public https URL of the media); language\_code (string, e.g. "en", "fr", "en\_us" — cannot be combined with language\_detection); language\_detection (boolean — detect the spoken language automatically); speech\_models (array of strings among "universal-3-5-pro", "universal-2", in priority order); punctuate (boolean); format\_text (boolean — casing and formatting; required true for redact\_pii); speaker\_labels (boolean — speaker diarization, needs punctuate); speakers\_expected (positive integer, needs speaker\_labels); disfluencies (boolean — keep filler words); filter\_profanity (boolean); multichannel (boolean); audio\_start\_from and audio\_end\_at (integers, milliseconds); keyterms\_prompt (array of strings — domain terms, max 6 words each); prompt (string — context for the universal-3-5-pro model); custom\_spelling (array of objects \{ from: array of strings, to: string }); auto\_highlights (boolean — key phrases); entity\_detection (boolean); iab\_categories (boolean — topic detection); sentiment\_analysis (boolean, needs punctuate); redact\_pii (boolean, needs format\_text true); redact\_pii\_policies (array of policy strings such as "person\_name", "email\_address", "phone\_number"); redact\_pii\_sub (string "entity\_name" or "hash"); redact\_pii\_audio (boolean — also produce a redacted audio copy, needs redact\_pii; read it with get\_redacted\_audio). |

## Permissions

Every action above must be explicitly granted to an agent before it can be used. See [Permissions](/integrations/permissions) for the grant model and [Security](/integrations/security) for how credentials are protected.

***

*Last reviewed against the provider API: September 2026.*


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.