We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
conversation.item.create
I've cached the items conversation, when syncing a page reload, to continue the conversation, or after 15min disconnect.
I tried sending user audio input, assistant text messages, 1 by 1.
The conversations get's received in items.events, but all the audio inputs sent, end up being returned as an empty Int16Array.
items.events
const addUserMessageAudio = (id: string, audio: Int16Array, text: string, previousItemId: string | undefined) => { console.log('~addUserMessageAudio', { id, text, previousItemId, audioLength: audio.length }); clientRef.current.realtime.send('conversation.item.create', { item: { type: 'message', role: 'user', status: 'completed', content: [{ type: 'input_audio', audio: RealtimeUtils.arrayBufferToBase64(audio), transcript: text }], // content: [{ type: 'input_text', text: text }], }, }); }
And if send the text, then when I speak to the model, it only responds with text, doesn't send any audio at that point.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
I've cached the items conversation, when syncing a page reload, to continue the conversation, or after 15min disconnect.
I tried sending user audio input, assistant text messages, 1 by 1.
The conversations get's received in
items.events
, but all the audio inputs sent, end up being returned as an empty Int16Array.And if send the text, then when I speak to the model, it only responds with text, doesn't send any audio at that point.
The text was updated successfully, but these errors were encountered: