Why does a Veo request not return the video straight away?

Because generation is a long-running operation. Generate Videos (Veo) starts the job, Get Videos Operation (Veo) reports where it is, Wait For Video (Veo) holds until it resolves, and Download Video (Veo) fetches the result - four separate actions for what looks like one step.

Which Veo model version does Lyro use?

Whichever the connected key exposes. List Models (Gemini API) is part of this toolkit precisely so the available model versions are read at call time rather than hardcoded, which matters when Google ships a new Veo revision.

Whose Google quota does a generation consume?

The Gemini API key you connect. Every generation Lyro submits bills to that key and counts against its limits, so video requests share a budget with anything else your team runs on the same credentials.

Can Lyro find a video that was generated last week?

Only if the operation reference from the original request was kept. This toolkit has no action that lists past generations, and no edit or delete action either, so the operation ID is the only handle on an earlier job.

Veo MCP integration

Submits a prompt as a Veo generation job, tracks the operation until it finishes, and downloads the finished clip.

Connect Veo See all integrations

5actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Generate videos (veo)
Lyro creates high-quality videos from text prompts to show product features or explain solutions. Your team delivers visual responses that make support interactions more engaging.
Get videos operation (veo)
Lyro checks the status of video generation jobs to know when content is ready. Your team stays informed without manually polling the API.
Download video (veo)
Lyro retrieves a finished video to send directly to customers. Your team shares completed content instantly without leaving Lyro's conversation.

See all 5 actions

How businesses use Veo + Lyro

Each card is one request a support team gets, and the Veo actions Lyro runs to close it.

Start a video generation from a written brief
Lyro checks which Veo model versions the connected Gemini API key exposes, then submits the prompt as a generation job so the request enters the queue as soon as it is made.
List Models (Gemini API)Generate Videos (Veo)
Follow the job through and deliver the file
Lyro polls the generation operation, or waits on it until it resolves, and downloads the finished clip once it is ready, so nobody has to keep checking a console for a job that takes minutes.
Get Videos Operation (Veo)Wait For Video (Veo)Download Video (Veo)

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Veo actions it has and picks the ones a request needs.

01
Connect Veo
Authorize the Veo account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Veo actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Veo · Lyro

Everything else about Veo

Setup, permissions, and the limits of what Lyro can do inside Veo.

Because generation is a long-running operation. Generate Videos (Veo) starts the job, Get Videos Operation (Veo) reports where it is, Wait For Video (Veo) holds until it resolves, and Download Video (Veo) fetches the result - four separate actions for what looks like one step.