Skip to main content

AssemblyAI Destination

Nexla's bi-directional connectors allow data to flow both to and from any location, making it simple to create a FlexFlow data flow that sends data to an AssemblyAI location.
assemblyai_api.png

AssemblyAI

Create an AssemblyAI Destination​

  1. Click the + icon on the Nexset that will be sent to the AssemblyAI destination, and select the Send to Destination option from the menu.

  2. Select the AssemblyAI connector from the list of available destination connectors. Then, select the credential that will be used to connect to the AssemblyAI account, and click Next; or, create a new AssemblyAI credential for use in this flow.

  3. In Nexla, AssemblyAI destinations can be created using pre-built endpoint templates, which expedite destination setup for common AssemblyAI endpoints. Each template is designed specifically for the corresponding AssemblyAI endpoint, making destination configuration easy and efficient.
    • To configure this destination using a template, follow the instructions in Configure Using a Template.

    AssemblyAI destinations can also be configured manually, allowing you to send data to AssemblyAI endpoints not included in the pre-built templates or apply further customizations to exactly suit your needs.
    • To configure this destination manually, follow the instructions in Configure Manually.

Configure Using a Template​

Nexla provides pre-built templates that can be used to rapidly configure destinations to send data to common AssemblyAI endpoints. Each template is designed specifically for the corresponding AssemblyAI endpoint, making destination setup easy and efficient.

  • To configure this destination using a template, select the endpoint to which data will be sent from the Endpoint pulldown menu. Then, click on the template in the list below to expand it, and follow the instructions to configure additional endpoint settings.

    Delete Transcript

    This endpoint deletes a transcript and its associated data — including the transcript text, words, and any audio intelligence outputs — from AssemblyAI. Use it to honor data retention policies, fulfill end-user deletion requests, or clean up test transcripts after evaluation.

    • Enter the transcript ID in the Transcript Id field. The default value substitutes the upstream record's id attribute, so the destination can be driven directly by a List Transcripts source filtered to the transcripts that should be removed.
    • Each call issues a DELETE against https://api.assemblyai.com/v2/transcript/{'{transcript_id}'}. The deletion is permanent and cannot be undone.

    Because deletion is irreversible, validate upstream data carefully before activating this destination. Consider running an upstream Nexla transform that filters to only the transcript IDs that should genuinely be deleted (for example, transcripts older than a configured retention window). For complete reference, see the Delete transcript documentation.

    Process Speech Understanding

    This endpoint submits a request to AssemblyAI's speech understanding service, which enables semantic understanding and analysis of spoken content. Use it to apply speech understanding to transcripts produced upstream — for example, by routing transcript IDs from a List Transcripts source into this destination.

    • Each call issues a POST to https://api.assemblyai.com/understanding with the upstream record as the JSON body. Use the Nexla transform layer to shape upstream attributes (transcript ID, feature flags, custom prompts) into the payload that the endpoint expects.
    • Speech understanding is a higher-level feature that may also be enabled at submission time on the Transcribe Audio endpoint by setting Speech Understanding to true. Use this destination when the upstream pipeline submits transcripts without that flag and you want to enrich them after the fact.

    Speech understanding is an evolving AssemblyAI surface. For the most current request body schema and supported features, see the Speech understanding documentation.

Configure Manually​

AssemblyAI destinations can be manually configured to send data to any valid AssemblyAI API endpoint. Manual configuration is the right choice when you need to call endpoints not covered by the pre-built templates — for example, to submit new transcription jobs (POST /v2/transcript), invoke the LLM Gateway (POST /chat/completions), or target the EU host at api.eu.assemblyai.com.

Using manual configuration, you can also configure Nexla to automatically send the response received from the AssemblyAI API after each call to a new Nexla webhook data source — useful for capturing newly created transcript IDs or LLM Gateway responses.

API Method​

  1. To manually configure this destination, select the Advanced tab at the top of the configuration screen.

  2. Select the API method that will be used for calls to the AssemblyAI API from the Method pulldown menu. AssemblyAI write operations typically use:

    • POST — to submit transcription jobs (/v2/transcript) or chat completion requests (/chat/completions).
    • DELETE — to remove transcripts (/v2/transcript/{'{transcript_id}'}).

Data Format​

  1. Select the format in which the Nexset data will be sent to the AssemblyAI API from the Content Format pulldown menu. AssemblyAI's REST API expects JSON request bodies, so JSON is the correct choice for all destination endpoints. Nexla will automatically convert the data to the selected format for each API call.

API Endpoint URL​

  1. Enter the URL of the AssemblyAI API endpoint to which you want to send the Nexset data in the URL field. AssemblyAI URLs use the base https://api.assemblyai.com/ followed by the resource path:

    • v2/transcript — submit a new transcription job
    • v2/transcript/<transcript_id> — delete an existing transcript (with DELETE)
    • chat/completions — call the LLM Gateway
    • understanding — submit a speech understanding request

    For path-parameterized endpoints (such as delete transcript), include the appropriate substitution token at the end of the URL — for example, https://api.assemblyai.com/v2/transcript/{'{{id}}'} substitutes the id attribute from each upstream record.

Request Headers​

Optional

  • If Nexla should include any additional request headers in API calls to this destination, enter the headers & corresponding values as comma-separated pairs in the Request Headers field (for example, header1:value1,header2:value2). AssemblyAI POST endpoints expect Content-Type:application/json, which Nexla sets automatically when the Content Format is JSON.

    You do not need to include any headers already present in the credentials. The Authorization header is added automatically based on your AssemblyAI credential.

Exclude Attributes from the Call​

Optional

  • If any record attributes in the Nexset should be omitted when sending data to this AssemblyAI destination, select the attributes from the Exclude Attributes pulldown menu. This is useful for stripping internal-only fields (for example, Nexla pipeline IDs or upstream join keys) before posting to AssemblyAI.

  • Any number of attributes can be selected for exclusion, and all excluded attributes will be shown in the field. To remove an attribute from the list, click the X icon next to the attribute name.

Record Batching​

Optional

  1. If records should be sent to this destination in batched API calls, check the box next to Would you like to batch your records together? to enable record batching.

  2. Enter the maximum number of records that should be batched together in a single API call in the Batch Size field. By default, this value is set to 100.

    The AssemblyAI REST endpoints accept one transcript or one chat completion per request, so batching is not applicable for the standard v2/transcript or chat/completions endpoints. Leave batching disabled when posting to those endpoints. Enable batching only when calling a custom endpoint that accepts an array payload.

  3. Select the algorithm that will be used to group records into batches from the Grouping Algorithm pulldown menu. The sample request shown in the panel on the right will be updated to reflect the current batching settings. Some algorithms require additional settings—click on an algorithm listed below to view instructions for configuring these settings.

Response Webhook​

Optional

Nexla can automatically send the response received from the AssemblyAI API after each call to a new Nexla webhook data source. This option allows you to keep track of the status of each API call and any additional information returned after each call — for example, capturing the new transcript IDs returned by POST /v2/transcript so they can flow back into a Get Transcript source downstream.

  • To enable this option, check the box next to Would you like to process the API response as a Nexla Webhook source?.

Sample Request Payload​

Sample request payloads containing a portion of the Nexset data that will be sent to the AssemblyAI API endpoint based on the current settings are shown in the Sample Payload panel on the right. These samples can be referenced to ensure that the destination and request settings are correctly configured.

  • Click on a sample request payload to expand it and view the complete payload content.
  • Sample payloads are automatically updated with each setting change, making it easy to verify that changes achieve the desired effect.

Endpoint Testing (Manual Configuration)​

After all endpoint settings have been configured, Nexla can send a test payload to the AssemblyAI API to ensure that the destination is configured correctly.

  1. To send a test payload, select the Test button at the top of the Sample Payload panel, and click on a listed sample payload to expand it.

  2. If any modifications to the sample payload are needed, make the necessary changes directly within the sample window.

  3. Click the Send Test Data button at the top of a sample payload to send the test payload to the AssemblyAI API using the current settings.

Save & Activate the Destination​

  • Once all endpoint settings have been configured, click the Done button in the upper right corner of the screen to save and create the destination. To begin sending data to the configured AssemblyAI endpoint, open the destination resource menu, and select Activate.

    The Nexset data will not be sent to AssemblyAI until the destination is activated. Destinations can be activated immediately or at a later time, providing full control over data movement.