---
canonical_url: "https://docs.composio.dev/toolkits/assemblyai"
markdown_url: "https://docs.composio.dev/toolkits/assemblyai.md"
product: "platform"
version: null
last_updated: null
---

# AssemblyAI

AssemblyAI provides speech-to-text transcription and audio intelligence APIs for uploaded and remotely hosted media.

- **Category:** audio & speech
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 9
- **Triggers:** 0
- **Slug:** `ASSEMBLYAI`
- **Version:** 20261014_00

## Tools

### Delete Transcript Content

**Slug:** `ASSEMBLYAI_DELETE_TRANSCRIPT`

Irreversibly 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `transcript_id` | string | Yes | Transcript whose stored audio and transcript content should be irreversibly deleted. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Export Subtitles

**Slug:** `ASSEMBLYAI_EXPORT_SUBTITLES`

Export a completed transcript as raw SRT or WebVTT subtitle text.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `transcript_id` | string | Yes | Completed transcript ID. |
| `subtitle_format` | string ("srt" | "vtt") | Yes | Subtitle document format: SRT or WebVTT. |
| `chars_per_caption` | integer | No | Target maximum characters per caption. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Redacted Audio

**Slug:** `ASSEMBLYAI_GET_REDACTED_AUDIO`

Get 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `transcript_id` | string | Yes | Transcript submitted with redact_pii=true, redact_pii_audio=true, and at least one explicit redact_pii_policies value. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Transcript

**Slug:** `ASSEMBLYAI_GET_TRANSCRIPT`

Retrieve an AssemblyAI transcript's current state and results, optionally waiting until asynchronous processing completes or fails.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `transcript_id` | string | Yes | Transcript ID returned by SUBMIT_TRANSCRIPT or LIST_TRANSCRIPTS. |
| `wait_for_completion` | boolean | No | Poll until status is completed or error. Set false to perform one status check. |
| `poll_timeout_seconds` | number | No | Maximum wall-clock wait when polling, from 1 to 900 seconds. |
| `poll_interval_seconds` | number | No | Delay between status checks, from 1 to 30 seconds. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Transcript Segments

**Slug:** `ASSEMBLYAI_GET_TRANSCRIPT_SEGMENTS`

Return sentence- or paragraph-level segments, timestamps, confidence, and words for a completed transcript.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `granularity` | string ("sentence" | "paragraph") | Yes | Whether to group the transcript into sentences or paragraphs. |
| `transcript_id` | string | Yes | Completed transcript ID. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Transcripts

**Slug:** `ASSEMBLYAI_LIST_TRANSCRIPTS`

List project transcripts from the last 90 days, newest first, with optional filters and a cursor for the next older page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum transcripts to return in this page (1-200). |
| `cursor` | string | No | Provider pagination URL from next_cursor or newer_cursor. Omit for the first page and pass it back unchanged. |
| `status` | string ("queued" | "processing" | "completed" | "error") | No | Only return transcripts in this processing state. |
| `created_on` | string | No | Only return transcripts created on this date. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Transcript

**Slug:** `ASSEMBLYAI_SEARCH_TRANSCRIPT`

Find words or phrases in a completed transcript and return occurrence counts and timestamps.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `terms` | array | Yes | Words or phrases to search for. Provide each term as a separate list item. |
| `transcript_id` | string | Yes | Completed transcript ID. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Submit Transcript

**Slug:** `ASSEMBLYAI_SUBMIT_TRANSCRIPT`

Queue 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `domain` | string | No | Use the medical transcription domain. |
| `webhook` | object | No | Callback invoked when processing finishes. |
| `language` | object | No | Language controls. Choose a known language or configure language detection. |
| `audio_url` | string | Yes | Reachable audio or video URL, including an upload_url returned by UPLOAD_MEDIA. |
| `prompting` | object | No | Context that improves recognition of names, terminology, and expected content. |
| `formatting` | object | No | Text formatting and cleanup options. |
| `audio_range` | object | No | Optional millisecond range to transcribe from the source. |
| `temperature` | number | No | Model sampling temperature from 0 to 1. |
| `intelligence` | object | No | Analysis features to compute with the transcript. |
| `pii_redaction` | object | No | PII redaction options for transcript text and audio. |
| `speech_models` | array | No | Model priority order; the default uses Universal-3.5 Pro with Universal-2 fallback. |
| `speech_threshold` | number | No | Speech confidence threshold from 0 to 1. |
| `speaker_detection` | object | No | Channel and speaker separation options. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Upload Media

**Slug:** `ASSEMBLYAI_UPLOAD_MEDIA`

Upload 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `media_file` | object | Yes | Audio or video file whose raw bytes should be uploaded. |
| `content_type` | string | No | MIME type for the media bytes, such as audio/mpeg or audio/wav. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |