Upload a media file to AssemblyAI’s servers.

Use the LeMUR task endpoint to input your own LLM prompt.

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

Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000.

Defaults to 2000. Max output size in tokens.

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

The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative.

A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower.

Custom Summary allows you to distill a piece of audio into a few impactful sentences. You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language.

Custom formatted transcript data. Maximum size is the context limit of the selected model

A list of completed transcripts with text.

Question & Answer allows you to ask free-form questions about a single transcript or a group of transcripts. The questions can be any whose answers you find useful, such as judging whether a caller is likely to become a customer or whether all items on a meeting’s agenda were covered.

Use LeMUR to generate a list of action items from a transcript.

How you want the action items to be returned. This can be any text. Defaults to “Bullet Points”.

Retrieve a LeMUR response that was previously generated.

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.

Create a temporary authentication token for Streaming Speech-to-Text.

The amount of time until the token expires in seconds

Create temporary authentication token for Streaming STT

Authenticate using a generated temporary token.

token

The encoding of the audio data. Defaults to pcm_s16le.

encoding

Add up to 2500 characters of custom vocabulary.

word_boost

sample_rate

Set to true to not receive partial transcripts. Defaults to false.

disable_partial_transcripts

Set to true to receive the SessionInformation message before the session ends. Defaults to false.

enable_extra_session_information

The unique identifier of your transcription

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.

Maximum amount of transcripts to retrieve.

limit

status

Get transcripts that were created after this transcript ID.

after_id

Get transcripts that were created before this transcript ID.

before_id

Only get transcripts created on this date.

created_on

Only get throttled transcripts, overrides the status filter.

throttled_only

Get the transcript resource. The transcript is ready when the “status” is “completed”.

Get the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.

Export your completed transcripts in SRT (srt) or VTT (vtt) format, which can be used for subtitles and closed captions in videos.

subtitle_format

If you enable PII redaction, get the redacted audio, as described in the Create a redacted audio file section.

Optionally, after your transcript is complete, get the paragraphs using its id.

Search through the transcript for keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.

words

AssemblyAI

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server. Bring your API credentials, configure and access your 3rd party APIs. Using LowCodeAPI securely manage all integrations in one place.