Basic Information

appmixer.ai.assemblyai.TranscribeAudio

Transcribe Audio

1.0.0

Public

Submit an audio or video URL for transcription. IMPORTANT: transcription is asynchronous — this returns a transcript id with status "queued", NOT the text. Use the Transcript Completed trigger (or poll with Get Transcript) to retrieve the result once processing finishes.

Input Ports

in

FieldTypeDescription
Audio URL text A publicly accessible URL of the audio/video file, or the upload_url returned by the Upload File component.
Speech Model select The speech model to use. Leave empty to use the default.
Language Code text The language of the audio, e.g. en, en_us, es. Leave empty and enable Language Detection to detect it automatically.
Language Detection toggle Automatically detect the spoken language.
Speaker Labels toggle Enable speaker diarization (who spoke when).
Speakers Expected number Hint for the expected number of speakers. Only used when Speaker Labels is enabled.
Multichannel toggle Transcribe each audio channel separately.
Punctuate toggle Enable automatic punctuation.
Format Text toggle Enable text formatting (casing, numbers, etc.).
Filter Profanity toggle Replace profanity in the transcript with asterisks.
Content Moderation toggle Audio Intelligence: detect sensitive content.
Topic Detection toggle Audio Intelligence: classify the transcript into IAB topic categories.
Entity Detection toggle Audio Intelligence: detect entities (people, organizations, locations, etc.).
Sentiment Analysis toggle Audio Intelligence: analyze sentiment for each spoken sentence.
Auto Highlights toggle Audio Intelligence: detect key phrases and words.
Redact PII toggle Remove personally identifiable information from the transcript text. Irreversible.
Redact PII Audio toggle Also produce a redacted version of the audio. Requires Redact PII to be enabled; retrieve it with Get Redacted Audio.
Webhook URL text Optional. AssemblyAI will POST { transcript_id, status } to this URL when processing finishes.

Output Ports

out

FieldTypeDescription
Transcript ID string -
Status string -
Audio URL string -

Full Metadata