Skip to content

feat(googleai): Add comprehensive model documentation and Veo 3 support #3162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

LyalinDotCom
Copy link

Summary

This PR enhances the Google AI plugin documentation by adding a comprehensive list of supported models and adding support for the Veo 3 video generation model.


Changes

Documentation Improvements

  • Added SUPPORTED_MODELS.md with a complete reference of all supported models including:
    • Text, multimodal, and live models (Gemini family)
    • Specialized models (Native Audio, TTS, Image Generation, Video Generation, Embeddings)
    • Clear tables showing model names, code references, capabilities, and notes.
    • Proper indication of Preview/Experimental status for models.
  • Updated README.md to include comprehensive usage examples for each model type:
    • Basic text generation
    • Multimodal generation with images
    • Image generation (Imagen 3 & 4)
    • Video generation (Veo 2 & 3)
    • Text-to-Speech
    • Native Audio models
    • Embeddings
    • Fine-tuned models

Code Changes

  • Updated KNOWN_VEO_MODELS type in veo.ts to include veo-3.0-generate-003.

Benefits

  • Developers can now easily discover all available supported models in one place.
  • Clear usage examples for each model category in the README.
  • Supports Veo 3 video generation model.
  • Emphasizes that the plugin uses dynamic model discovery for automatic support of new models.

Testing

The changes are documentation-focused with a minor type update. The Veo 3 model will work through the existing dynamic model discovery mechanism when available in the API.

@github-actions github-actions bot added docs Improvements or additions to documentation js labels Jul 4, 2025
@LyalinDotCom
Copy link
Author

my long lived dream of listing supported models ....


```ts
// Using Veo 2
const videoResponse = await ai.generate({
Copy link
Collaborator

@pavelgj pavelgj Jul 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is not quite right/complete. Refer to

let { operation } = await ai.generate({

More specifically, you need to get the operation:

const { operation } = await ai.generate(...)

and then check the operation status:

  while (!operation.done) {
    sendChunk('check status of operation ' + operation.id);
    operation = await ai.checkOperation(operation);
    await new Promise((resolve) => setTimeout(resolve, 5000));
  }

and then download the video...

async function downloadVideo(video: MediaPart, path: string) {


```ts
// Using Imagen
const imageResponse = await ai.generate({
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

probably best to use

const { media } = await ai.generate(...)

See:

const { media } = await ai.generate({


```ts
// Using Gemini TTS
const audioResponse = await ai.generate({
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Refer to example here:

const { media } = await ai.generate({

const { media } = await ai.generate(...)

but then it requires conversion from PCM to WAV format to be usable:

async function toWav(

});
```

### Native Audio (Conversational)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we don't support this....

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

AI thinks we should...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
docs Improvements or additions to documentation js
Projects
Status: No status
Development

Successfully merging this pull request may close these issues.

2 participants