AssemblyAI

api.assemblyai.com

Community

Speech-to-text and audio intelligence API. Transcribe audio/video, speaker diarization, sentiment analysis, entity detection, summarization, PII redaction, and LLM-powered audio understanding.

[catalog]Catalog only — enable via gateway with your own API key

Enable this service

This service is in the catalog but not part of v1 launch billing. To use it, run the command below and provide your own API key in the local config page — the gateway will call it under your account.

Auth

api_key

Pricing

free

Spec version

1.0

Base URL

https://api.assemblyai.com

Last crawled

May 4, 2026

Health

This is a community-maintained manifest. Health monitoring is not available because this service doesn't host its own /.well-known/agent endpoint yet. Learn more about trust levels →

Top Capabilities

Most commonly used operations — ready to call without drill-down.

transcripts_list

GET

List all transcripts with pagination and status filters.

GET https://api.assemblyai.com/v2/transcript

limit (integer) — Maximum transcripts to retrieve.

status (string) — Filter by status: queued, processing, completed, error.

created_on (string) — Filter by creation date.

before_id (string) — Get transcripts before this ID.

after_id (string) — Get transcripts after this ID.

...and 1 more parameters

transcripts_get

GET

Retrieve a transcript by ID. Poll this endpoint until status is 'completed' or 'error'.

GET https://api.assemblyai.com/v2/transcript/{transcript_id}

transcript_id (string, required) — Transcript ID.

transcripts_word_search

GET

Search for specific words or phrases in a transcript.

GET https://api.assemblyai.com/v2/transcript/{transcript_id}/word-search

transcript_id (string, required) — Transcript ID.

words (string, required) — Comma-separated words to search for.

All Capabilities (17)

files (1)

POSTfiles_upload

Upload a local audio/video file for transcription. Returns a temporary URL accessible only by AssemblyAI.

lemur (5)

POSTlemur_action_items

Extract action items from one or more transcripts using LeMUR.

DELETElemur_purge

Purge LeMUR request data for a specific request ID.

POSTlemur_question_answer

Ask questions about one or more transcripts using LeMUR.

POSTlemur_summary

Generate an automatic summary of one or more transcripts using LeMUR.

POSTlemur_task

Run a custom LLM task on one or more transcripts using LeMUR.

realtime (1)

POSTrealtime_token_create

Generate a temporary authentication token for real-time streaming transcription.

transcripts (10)

POSTtranscripts_create

Submit an audio/video file for transcription. Supports speaker diarization, sentiment analysis, entity detection, summarization, and PII redaction.

DELETEtranscripts_delete

Delete a transcript and any uploaded audio files associated with it.

GETtranscripts_get

Retrieve a transcript by ID. Poll this endpoint until status is 'completed' or 'error'.

GETtranscripts_list

List all transcripts with pagination and status filters.

GETtranscripts_paragraphs

Get the transcript split into paragraphs with timestamps.

GETtranscripts_redacted_audio

Get a redacted version of the audio with PII bleeped out.

GETtranscripts_sentences

Get the transcript split into sentences with timestamps.

GETtranscripts_subtitles_srt

Get the transcript as SRT subtitles.

GETtranscripts_subtitles_vtt

Get the transcript as VTT subtitles.

GETtranscripts_word_search

Search for specific words or phrases in a transcript.

Agent Preview

This is what an AI agent sees when it discovers this service via the Gateway:

Service: AssemblyAI
Description: Speech-to-text and audio intelligence API. Transcribe audio/video, speaker diarization, sentiment analysis, entity detection, summarization, PII redaction, and LLM-powered audio understanding.
Auth: api_key
Capabilities (17 total):
  files (1):
    - files_upload: Upload a local audio/video file for transcription. Returns a temporary URL accessible only by AssemblyAI.
  lemur (5):
    - lemur_action_items: Extract action items from one or more transcripts using LeMUR.
    - lemur_purge: Purge LeMUR request data for a specific request ID.
    - lemur_question_answer: Ask questions about one or more transcripts using LeMUR.
    - lemur_summary: Generate an automatic summary of one or more transcripts using LeMUR.
    - lemur_task: Run a custom LLM task on one or more transcripts using LeMUR.
  realtime (1):
    - realtime_token_create: Generate a temporary authentication token for real-time streaming transcription.
  transcripts (10):
    - transcripts_create: Submit an audio/video file for transcription. Supports speaker diarization, sentiment analysis, entity detection, summarization, and PII redaction.
    - transcripts_delete: Delete a transcript and any uploaded audio files associated with it.
    - transcripts_get: Retrieve a transcript by ID. Poll this endpoint until status is 'completed' or 'error'.
    - transcripts_list: List all transcripts with pagination and status filters.
    - transcripts_paragraphs: Get the transcript split into paragraphs with timestamps.
    - transcripts_redacted_audio: Get a redacted version of the audio with PII bleeped out.
    - transcripts_sentences: Get the transcript split into sentences with timestamps.
    - transcripts_subtitles_srt: Get the transcript as SRT subtitles.
    - transcripts_subtitles_vtt: Get the transcript as VTT subtitles.
    - transcripts_word_search: Search for specific words or phrases in a transcript.

Top capabilities (ready to call):
  - transcripts_list: GET /v2/transcript
  - transcripts_get: GET /v2/transcript/{transcript_id}
  - transcripts_word_search: GET /v2/transcript/{transcript_id}/word-search