AssemblyAI
Transcribe audio and summarize content using AssemblyAI.
On this page
Connect
Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.
- In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
- For every project in a workspace: Workspace settings, Integrations.
- Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.
Call it from a workflow
Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.
// .workflow.js (native ctx)
export async function run(ctx) {
const res = await ctx.integrations.invoke("assemblyai", "deleteTranscript", {
"id": "<transcript id>"
});
if (!res.success) throw new Error(res.error);
ctx.log.info("AssemblyAI answered", { output: res.output });
}// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";
export default defineWorkflow({
id: "assemblyai-deletetranscript",
name: "AssemblyAI: Delete transcript",
description: "Calls AssemblyAI when a row is created.",
trigger: { type: "entity_event", entity: "tickets", event: "created" },
async run(ctx, event) {
const res = await ctx.integrations.call("assemblyai", {
"action": "deleteTranscript",
"id": "<transcript id>"
}) as { success: boolean; error?: string };
if (!res.success) throw new Error(res.error);
},
});curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/assemblyai/deleteTranscript" \
-H "Authorization: Bearer $APP_KEY" \
-H "content-type: application/json" \
-d '{"props":{"id":"<transcript id>"}}'Actions
deleteTranscriptin catalog
Delete transcript. Remove the data from the transcript and mark it as deleted.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
getLemurResponsein catalog
Retrieve LeMUR response. Retrieve a LeMUR response that was previously generated.
| Input | Type | Description |
|---|---|---|
request_idrequired | text | The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request. |
getRedactedAudioin catalog
Get Transcript Redacted Audio. Get the result of the redacted audio model.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
download_filerequired | boolean | Download file? |
download_file_namerequired | text | The desired file name for storing in ActivePieces. Make sure the file extension is correct. |
getSubtitlesin catalog
Get Transcript Subtitles. Export the transcript as SRT or VTT subtitles.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
formatrequired | one of "srt" | "vtt" | Subtitles Format |
chars_per_captionoptional | number | The maximum number of characters per caption |
getTranscriptin catalog
Get Transcript. Retrieves a transcript by its ID.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
getTranscriptParagraphsin catalog
Get Transcript Paragraphs. Retrieve the paragraphs of the transcript by its ID.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
custom_api_call
Custom API Call. Make a custom API call to a specific endpoint
| Input | Type | Description |
|---|---|---|
urlrequired | object (depends on other props) | url |
methodrequired | one of "GET" | "POST" | "PATCH" | "PUT" | "DELETE" | "HEAD" | Method |
headersrequired | object | Authorization headers are injected automatically from your connection. |
queryParamsrequired | object | Query Parameters |
body_typeoptional | one of "none" | "json" | "form_data" | "raw" | Body Type |
bodyoptional | object (depends on other props) | Body |
response_is_binaryoptional | boolean | Enable for files like PDFs, images, etc. |
failsafeoptional | boolean | No Error on Failure |
timeoutoptional | number | Timeout (in seconds) |
followRedirectsoptional | boolean | Follow redirects |
getTranscriptSentences
Get Transcript Sentences. Retrieve the sentences of the transcript by its ID.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
lemurTask
Run a Task using LeMUR. Use the LeMUR task endpoint to input your own LLM prompt.
| Input | Type | Description |
|---|---|---|
promptrequired | text | Your text to prompt the model to produce a desired output, including any context you want to pass into the model. |
transcript_idsoptional | array | A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR. |
input_textoptional | text | Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR. |
contextoptional | long text | Context to provide the model. This can be a string or a free-form JSON value. |
final_modeloptional | one of "anthropic/claude-3-5-sonnet" | "anthropic/claude-3-opus" | "anthropic/claude-3-haiku" | "anthropic/claude-3-sonnet" | "anthropic/claude-2-1" | "anthropic/claude-2" | "default" | "anthropic/claude-instant-1-2" | "basic" | "assemblyai/mistral-7b" | The model that is used for the final prompt after compression is performed. |
max_output_sizeoptional | number | Max output size in tokens, up to 4000 |
temperatureoptional | number | The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive. |
listTranscripts
List transcripts. Retrieve a list of transcripts you created. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.
| Input | Type | Description |
|---|---|---|
limitoptional | number | Maximum amount of transcripts to retrieve |
statusoptional | one of "queued" | "processing" | "completed" | "error" | Filter by transcript status |
created_onoptional | date-time (ISO) | Only get transcripts created on this date |
before_idoptional | text | Get transcripts that were created before this transcript ID |
after_idoptional | text | Get transcripts that were created after this transcript ID |
throttled_onlyoptional | boolean | Only get throttled transcripts, overrides the status filter |
purgeLemurRequestData
Purge LeMUR request data. Delete the data for a previously submitted LeMUR request. The LLM response data, as well as any context provided in the original request will be removed.
| Input | Type | Description |
|---|---|---|
request_idrequired | text | The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request. |
transcribe
Transcribe. Transcribe an audio or video file using AssemblyAI.
| Input | Type | Description |
|---|---|---|
audio_urlrequired | text | The URL of the audio or video file to transcribe. |
language_codeoptional | one of "en" | "en_au" | "en_uk" | "en_us" | "es" | "fr" | "de" | "it" | "pt" | "nl" | "af" | "sq" | The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages). The default value is 'en_us'. |
language_detectionoptional | boolean | Enable [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection), either true or false. |
language_confidence_thresholdoptional | number | The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0. |
speech_modeloptional | one of "best" | "nano" | The speech model to use for the transcription. When `null`, the "best" model is used. |
punctuateoptional | boolean | Enable Automatic Punctuation, can be true or false |
format_textoptional | boolean | Enable Text Formatting, can be true or false |
disfluenciesoptional | boolean | Transcribe Filler Words, like "umm", in your media file; can be true or false |
dual_channeloptional | boolean | Enable [Dual Channel](https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) transcription, can be true or false. |
webhook_urloptional | text | The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if … |
webhook_auth_header_nameoptional | text | The header name to be sent with the transcript completed or failed webhook requests |
webhook_auth_header_valueoptional | text | The header value to send back with the transcript completed or failed webhook requests for added security |
auto_highlightsoptional | boolean | Enable Key Phrases, either true or false |
audio_start_fromoptional | number | The point in time, in milliseconds, to begin transcribing in your media file |
audio_end_atoptional | number | The point in time, in milliseconds, to stop transcribing in your media file |
word_boostoptional | array | The list of custom vocabulary to boost transcription probability for |
boost_paramoptional | one of "low" | "default" | "high" | How much to boost specified words |
filter_profanityoptional | boolean | Filter profanity from the transcribed text, can be true or false |
redact_piioptional | boolean | Redact PII from the transcribed text using the Redact PII model, can be true or false |
redact_pii_audiooptional | boolean | Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details. |
uploadFile
Upload File. Upload a media file to AssemblyAI's servers.
| Input | Type | Description |
|---|---|---|
filerequired | file | The File or URL of the audio or video file. |
wordSearch
Search words in transcript. Search through the transcript for keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.
| Input | Type | Description |
|---|---|---|
idrequired | text | Transcript ID |
wordsrequired | array | Keywords to search for |
Details
- Id
assemblyai- Category
- AI and ML
- Tags
- speech, transcription, summarization, audio, ai
- Package
@activepieces/piece-assemblyai@1.1.4- Tier
- Community