AssemblyAI AI Voice Call Automation

Your text to prompt the model to produce a desired output, including any context you want to pass into the model.

Context to provide the model. This can be a string or a free-form JSON value.

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.

The model that is used for the final prompt after compression is performed.

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.

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.

Max output size in tokens, up to 4000

The list of custom topics

The URL of the audio or video file to transcribe.

Enable Automatic Punctuation, can be true or false

Redact PII from the transcribed text using the Redact PII model, can be true or false

The list of custom vocabulary to boost transcription probability for

How much to boost specified words

Enable Text Formatting, can be true or false

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 redact_pii_audio is enabled.

The point in time, in milliseconds, to stop transcribing in your media file

Transcribe Filler Words, like "umm", in your media file; can be true or false

Enable [Dual Channel](https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) transcription, can be true or false.

The speech model to use for the transcription. When `null`, the "best" model is used.

The type of summary

Enable [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters), can be true or false

Enable custom topics, either true or false

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'.

Enable [Summarization](https://www.assemblyai.com/docs/models/summarization), can be true or false

The model to summarize the transcript

Enable [Content Moderation](https://www.assemblyai.com/docs/models/content-moderation), can be true or false

Enable [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection), can be true or false

The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

Enable [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization), can be true or false

If the transcript status is "error", throw an error.

Enable Key Phrases, either true or false

Customize how words are spelled and formatted using to and from values. Use a JSON array of objects of the following format: ``` [ { "from": ["original", "spelling"], "to": "corrected" } ] ```

The point in time, in milliseconds, to begin transcribing in your media file

Enable [Entity Detection](https://www.assemblyai.com/docs/models/entity-detection), can be true or false

Filter profanity from the transcribed text, can be true or false

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.

Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.

Wait until the transcript status is "completed" or "error" before moving on to the next step.

Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for more details.

Enable [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection), either true or false.

Enable [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis), can be true or false

The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

The header name to be sent with the transcript completed or failed webhook requests

The confidence threshold for the Content Moderation model. Values must be between 25 and 100.

The header value to send back with the transcript completed or failed webhook requests for added security

The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0.

The File or URL of the audio or video file.

Keywords to search for

The maximum number of characters per caption

Authorization headers are injected automatically from your connection.

Maximum amount of transcripts to retrieve

Filter by transcript status

Get transcripts that were created after this transcript ID

Get transcripts that were created before this transcript ID

Only get transcripts created on this date

Only get throttled transcripts, overrides the status filter

The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request.

The desired file name for storing in ActivePieces. Make sure the file extension is correct.

The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request.