Tavus connector

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

Written By Lauri Raivio

Last updated 16 days ago

Kaivo is a fully managed data platform that syncs your Tavus 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 Tavus instead of moving it.

What is the Tavus connector

Sync your Tavus replicas, videos, and conversations into BigQuery with Kaivo to track AI video generation and usage.

Category	Tech
Authentication	API key
Setup	Self-service

Getting started with the Tavus connector

Sign up for Kaivo and create a workspace.
Connect your Tavus account.
Choose which tables to sync.
Wait for the initial sync to finish.
Query your data in BigQuery or your favourite AI or BI tool.

Authenticating Tavus

Authenticate with your API Key.

Field	Description
API Key	Your Tavus API key. You can find this in your Tavus account settings or API dashboard.

Configuring the Tavus connector

When you set up the connector, you provide:

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

Tables and columns synced from Tavus

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

conversations (9 columns)

Column	Type	Description
`_kaivo_id`	`STRING`	Primary key that uniquely identifies the row. Auto-generated by Kaivo.
`conversation_id`	`STRING`
`conversation_name`	`STRING`
`conversation_url`	`STRING`
`created_at`	`STRING`
`replica_id`	`STRING`
`status`	`STRING`
`updated_at`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

personas (23 columns)

Column	Type	Description
`_kaivo_id`	`STRING`	Primary key that uniquely identifies the row. Auto-generated by Kaivo.
`context`	`STRING`
`created_at`	`STRING`
`default_replica_id`	`STRING`
`layers__llm__speculative_inference`	`BOOL`
`layers__perception__perception_model`	`STRING`
`layers__stt__participant_interrupt_sensitivity`	`STRING`
`layers__stt__participant_pause_sensitivity`	`STRING`
`layers__stt__smart_turn_detection`	`BOOL`
`layers__stt__stt_engine`	`STRING`
`layers__transport__input_settings__microphone`	`STRING`
`layers__transport__room_settings__enable_chat`	`BOOL`
`layers__transport__room_settings__enable_network_ui`	`BOOL`
`layers__transport__room_settings__enable_noise_cancellation_ui`	`BOOL`
`layers__transport__room_settings__enable_people_ui`	`BOOL`
`layers__transport__room_settings__start_audio_off`	`BOOL`
`layers__transport__room_settings__start_video_off`	`BOOL`
`persona_id`	`STRING`
`persona_name`	`STRING`
`pipeline_mode`	`STRING`
`system_prompt`	`STRING`
`updated_at`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

Subtable: personaslayersperception__ambient_awareness_queries

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.
`value`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

replicas (10 columns)

Column	Type	Description
`_kaivo_id`	`STRING`	Primary key that uniquely identifies the row. Auto-generated by Kaivo.
`created_at`	`STRING`
`model_name`	`STRING`
`replica_id`	`STRING`
`replica_name`	`STRING`
`status`	`STRING`
`thumbnail_video_url`	`STRING`
`training_progress`	`STRING`
`updated_at`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

speeches (6 columns)

Column	Type	Description
`_kaivo_id`	`STRING`	Primary key that uniquely identifies the row. Auto-generated by Kaivo.
`speech_id`	`STRING`
`speech_name`	`STRING`
`speech_file_url`	`STRING`
`replica_id`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

videos (16 columns)

Column	Type	Description
`_kaivo_id`	`STRING`	Primary key that uniquely identifies the row. Auto-generated by Kaivo.
`created_at`	`STRING`
`data__script`	`STRING`
`download_url`	`STRING`
`generation_progress`	`STRING`
`gif_thumbnail_url`	`STRING`
`hosted_url`	`STRING`
`replica_id`	`STRING`
`status`	`STRING`
`status_details`	`STRING`
`still_image_thumbnail_url`	`STRING`
`stream_url`	`STRING`
`updated_at`	`STRING`
`video_id`	`STRING`
`video_name`	`STRING`
`_kaivo_extracted_at`	`TIMESTAMP`	Timestamp that shows when the row was extracted. Auto-generated by Kaivo.

How the Tavus sync works

After the first load, Kaivo keeps your BigQuery warehouse up to date for you. Where Tavus 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.

Frequently asked questions

How long does the initial sync take for Tavus?

It depends on how much history is in your Tavus 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.

Can I sync only some tables or columns?

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 Tavus'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 Tavus, 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.

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 Tavus 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 Tavus connector in Kaivo and all of its synced data is deleted with it.

Common use cases for Tavus data

Video output

Use videos with status and generation_progress to track how much content you generate.

Replica inventory

Report on replicas by status and training_progress to see what is ready to use.

Conversation activity

Use conversations to monitor live AI video sessions.

Persona usage

Report on personas to see which configurations you use most.

Use Tavus data in your AI and BI tools

Once Tavus 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 Tavus data.

Claude

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

Power BI

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

Data Studio

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

Tableau

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

Google Sheets

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

Excel

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

Metabase

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

See our pricing page for Tavus 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.

Was this helpful?

Still need help? Share an idea