Skip to content
Book a demoStart free
Connectors

AssemblyAI connector

Set up the AssemblyAI connector in Kaivo: authentication, configuration, the 5 BigQuery tables it syncs, and answers to common questions.

AssemblyAI connector pricing, tier and credits on kaivo.io

Kaivo is a fully managed data platform that syncs your AssemblyAI data into a Google BigQuery warehouse and keeps it up to date automatically. There is no pipeline to build and no infrastructure to run, so you can spend your time analysing your data from AssemblyAI instead of moving it.

Sync your AssemblyAI transcription data into BigQuery with Kaivo to analyse transcripts and speech insights at scale.

CategoryTech
AuthenticationAPI key
SetupSelf-service

Getting started with the AssemblyAI connector

Section titled “Getting started with the AssemblyAI connector”
  1. Sign up for Kaivo and create a workspace.
  2. Connect your AssemblyAI account.
  3. Choose which tables to sync.
  4. Wait for the initial sync to finish.
  5. Query your data in BigQuery or your favourite AI or BI tool.

Authenticate with your API Key.

Field Description
API Key
Your AssemblyAI API key, found in the AssemblyAI dashboard.

|

When you set up the connector, you provide:

Field Description
Start Date
Any data before this date will not be fetched.

| | Subtitle Format |

File format for subtitles generated from your transcripts: srt (SubRip) or vtt (WebVTT).

| | LeMUR Request ID |

Optional. The ID of a LeMUR request (returned when you run a LeMUR task) whose response you want to sync. Leave empty if you don’t use LeMUR.

|

Kaivo syncs 5 tables from AssemblyAI into a dedicated dataset in your BigQuery warehouse. Click any table to see its columns and types.

lemur_response (6 columns)
Column Type Description
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
request_id STRING
response STRING
usage__input_tokens FLOAT64
usage__output_tokens FLOAT64
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
paragraphs (7 columns)
Column Type Description
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
confidence FLOAT64
end FLOAT64
start FLOAT64
text STRING
uuid STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
Column Type Description
_kaivo_parent_id STRING Foreign key referencing _kaivo_id in the parent table. Auto-generated by Kaivo.
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
confidence FLOAT64
end FLOAT64
start FLOAT64
text STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
transcript_sentences (7 columns)
Column Type Description
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
confidence FLOAT64
end FLOAT64
start FLOAT64
text STRING
uuid STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
Column Type Description
_kaivo_parent_id STRING Foreign key referencing _kaivo_id in the parent table. Auto-generated by Kaivo.
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
confidence FLOAT64
end FLOAT64
start FLOAT64
text STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
transcript_subtitle (5 columns)
Column Type Description
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
redacted_audio_url STRING
status STRING
uuid STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.
transcripts (9 columns)
Column Type Description
_kaivo_id STRING Primary key that uniquely identifies the row. Auto-generated by Kaivo.
audio_url STRING
completed STRING
created STRING
error STRING
id STRING
resource_url STRING
status STRING
_kaivo_extracted_at TIMESTAMP Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

After the first load, Kaivo keeps your BigQuery warehouse up to date for you. Where AssemblyAI supports it, each sync pulls only new and changed records so it stays fast; otherwise it refreshes the whole table. Every record keeps its original ID, so you won’t get duplicate rows.

How long does the initial sync take for AssemblyAI?

Section titled “How long does the initial sync take for AssemblyAI?”

It depends on how much history is in your AssemblyAI account. Most initial syncs finish within minutes, while large accounts can take a few hours. After that, syncs only fetch new and changed records, so they’re much faster.

Yes. You pick which tables to sync when you set up the connection and can change the selection later. Tables you don’t select are never copied to your warehouse.

What happens when AssemblyAI’s schema changes?

Section titled “What happens when AssemblyAI’s schema changes?”

New fields are never added automatically. You choose which fields to sync, so data you haven’t selected (sensitive personal data, for example) never lands in your warehouse. When a new field appears, it becomes available for you to add. What happens to removed or renamed fields depends on a table’s sync mode: full-refresh tables always match what’s currently in AssemblyAI, so dropped fields disappear, while incremental tables keep their existing columns and history, so an old field stays and newly added fields fill in over time.

How do I handle GDPR or data deletion requests?

Section titled “How do I handle GDPR or data deletion requests?”

Your data lives in your own Kaivo-managed BigQuery warehouse, so the most direct option is to delete or anonymise specific records right in BigQuery. If you delete data in AssemblyAI instead, full-refresh tables drop it on the next sync, while incremental tables keep it, so you would remove the row in BigQuery or ask us to run a full refresh. To remove everything, delete the AssemblyAI connector in Kaivo and all of its synced data is deleted with it.

Use transcripts and transcript_sentences to search and analyse what was said across recordings.

Bring paragraphs and lemur_response into BigQuery to extract themes and summaries.

Use transcript_subtitle to manage captions across your media library.

Use AssemblyAI data in your AI and BI tools

Section titled “Use AssemblyAI data in your AI and BI tools”

Once AssemblyAI data lands in your Kaivo-managed BigQuery warehouse, you can explore it with AI tools or any BI tool that connects to BigQuery. Here’s how the most common destinations work with AssemblyAI data.

Use Kaivo’s MCP server to give Claude secure, workspace-scoped access to your data. Setup guide →

Microsoft’s BI tool with a native BigQuery connector. Supports direct query and scheduled refresh. Setup guide →

Free Google BI tool with native BigQuery support. One-click connection to your Kaivo warehouse; great for SMB teams on Google Workspace. Setup guide →

The premium analytics standard, with native BigQuery integration. Setup guide →

Use Connected Sheets to query BigQuery directly from a spreadsheet, with no SQL. Setup guide →

Connect via Power Query’s BigQuery connector. Setup guide →

Open-source BI tool with strong BigQuery support. Setup guide →

See our pricing page for AssemblyAI connector pricing and plan details.

  • Adform: Sync Adform to BigQuery.
  • Amplitude: Sync Amplitude to BigQuery.
  • Auth0: Sync Auth0 to BigQuery.
  • Convex: Sync Convex to BigQuery.
  • GitHub: Sync GitHub to BigQuery.
  • GitLab: Sync GitLab to BigQuery.