Skip to main content
AssemblyAI logo
  • Category: audio & speech
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 9
  • Triggers: 0
  • Slug: ASSEMBLYAI
  • Version: 20261101_00

Tools

Slug: ASSEMBLYAI_DELETE_TRANSCRIPTIrreversibly delete a transcript’s stored content. AssemblyAI retains a tombstone that later GET and list calls can still return, and those later responses may omit the is_deleted marker.

Input Parameters

string
required
Transcript whose stored audio and transcript content should be irreversibly deleted.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_EXPORT_SUBTITLESExport a completed transcript as raw SRT or WebVTT subtitle text.

Input Parameters

string
required
Completed transcript ID.
string ("srt" | "vtt")
required
Subtitle document format: SRT or WebVTT.
integer
Target maximum characters per caption.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_GET_REDACTED_AUDIOGet the processing status and short-lived signed download URL for PII-redacted audio. The transcript must have been submitted with text and audio PII redaction enabled and at least one explicit redaction policy. Treat the returned URL as transient and do not log, cache, or persist it.

Input Parameters

string
required
Transcript submitted with redact_pii=true, redact_pii_audio=true, and at least one explicit redact_pii_policies value.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_GET_TRANSCRIPTRetrieve an AssemblyAI transcript’s current state and results, optionally waiting until asynchronous processing completes or fails.

Input Parameters

string
required
Transcript ID returned by SUBMIT_TRANSCRIPT or LIST_TRANSCRIPTS.
boolean
Poll until status is completed or error. Set false to perform one status check.
number
Maximum wall-clock wait when polling, from 1 to 900 seconds.
number
Delay between status checks, from 1 to 30 seconds.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_GET_TRANSCRIPT_SEGMENTSReturn sentence- or paragraph-level segments, timestamps, confidence, and words for a completed transcript.

Input Parameters

string ("sentence" | "paragraph")
required
Whether to group the transcript into sentences or paragraphs.
string
required
Completed transcript ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_LIST_TRANSCRIPTSList project transcripts from the last 90 days, newest first, with optional filters and a cursor for the next older page.

Input Parameters

integer
Maximum transcripts to return in this page (1-200).
string
Provider pagination URL from next_cursor or newer_cursor. Omit for the first page and pass it back unchanged.
string ("queued" | "processing" | "completed" | "error")
Only return transcripts in this processing state.
string
Only return transcripts created on this date.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_SEARCH_TRANSCRIPTSearch a completed transcript for words or phrases of up to five words and return occurrence counts and timestamps.

Input Parameters

array
required
Words or phrases to search for. Provide each term as a separate list item.
string
required
Completed transcript ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_SUBMIT_TRANSCRIPTQueue an asynchronous pre-recorded transcription from a reachable media URL. Returns immediately with the transcript ID and processing status; use GET_TRANSCRIPT to wait for results.

Input Parameters

string
Use the medical transcription domain.
object
Callback invoked when processing finishes.
object
Language controls. Choose a known language or configure language detection.
string
required
Reachable audio or video URL, including an upload_url returned by UPLOAD_MEDIA.
object
Context that improves recognition of names, terminology, and expected content.
object
Text formatting and cleanup options.
object
Optional millisecond range to transcribe from the source.
number
Model sampling temperature from 0 to 1.
object
Analysis features to compute with the transcript.
object
PII redaction options for transcript text and audio.
array
Model priority order; the default uses Universal-3.5 Pro with Universal-2 fallback.
number
Speech confidence threshold from 0 to 1.
object
Channel and speaker separation options.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: ASSEMBLYAI_UPLOAD_MEDIAUpload an audio or video file to AssemblyAI and return the project-private URL to use when submitting a transcript. AssemblyAI provides no API to delete this uploaded object; it remains subject to provider retention.

Input Parameters

object
required
Audio or video file whose raw bytes should be uploaded.
string
MIME type for the media bytes, such as audio/mpeg or audio/wav.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not