Skip to content

fix(js/plugin/compat-oai): invalid model ID error in transcription models #4708

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.

Sign up for GitHub

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

Merged
ifielker merged 2 commits into from
Feb 18, 2026
Merged

fix(js/plugin/compat-oai): invalid model ID error in transcription models #4708

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ab92c4f
fix: invalid model ID error in transcription models
7hokerz Feb 17, 2026
652da76
feat: change audio file
7hokerz Feb 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions js/plugins/compat-oai/src/audio.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,15 +358,16 @@ export function defineCompatOpenAITranscriptionModel<
requestBuilder?: TranscriptionRequestBuilder;
}): ModelAction {
const {
name: modelName,
name,
pluginOptions,
client: defaultClient,
modelRef,
requestBuilder,
} = params;

const modelName = toModelName(name, pluginOptions?.name);
const actionName =
modelRef?.name ?? `${pluginOptions?.name ?? 'compat-oai'}/${modelName}`;

return model(
{
name: actionName,
Expand Down
Binary file added js/testapps/compat-oai/jfk.flac
View file
Open in desktop
Binary file not shown.
19 changes: 19 additions & 0 deletions js/testapps/compat-oai/src/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,6 +358,25 @@ async function toWav(
});
}

// STT sample
ai.defineFlow('transcribe', async () => {
const audioFile = fs.readFileSync('jfk.flac');

const { text } = await ai.generate({
model: openAI.model('whisper-1'),
prompt: [
{
media: {
contentType: 'audio/flac',
url: `data:audio/flac;base64,${audioFile.toString('base64')}`,
},
},
],
});

return text;
});

// PDF file input example
ai.defineFlow(
{
Expand Down