Thanks. No, in fact I do not get a voice response at all from voice input. This is the result of selecting the microphone, activating the plugin, talking to the app, hearing no response. Have not sent a text message.
Please send me in DM the page of your app I may test.
Checking to see if you got the DM.
Yes I did. Will follow up privately.
Hey Bubblers!
Informing you that I have released an interruption improvement. Now the model stops immediately if one speaks over it, like on OpenAI Playground.
Enjoy!
Good news! OpenAI cuts its prices for Realtime API (as expected ).
Plus new voices.
Hey,
Following OpenAI Realtime API’s changes for interrupts, a fix has been released today.
For those who had an error after interrupt, this fix adresses this issue.
Hey guys,
I’m pleased to share that the plugin has undergone performance improvements, resulting in notably faster response times for more reactive conversations and improved accuracy in remembering past history.
Enjoy!
Also, again, another price cut is coming up
Starting January 9, the Realtime API will point to our latest model snapshot
gpt-4o-realtime-preview-2024-12-17
by default. This snapshot reduces the audio token price by 60% to $40/1M input tokens and $80/1M output tokens. Cached audio input costs are reduced by 87.5% to $2.50/1M input tokens. We’ve also improved voice quality and made inputs more reliable, especially for dictated numbers.gpt-4o-audio-preview
will also be updated to point to thegpt-4o-audio-preview-2024-12-17
.
Hey Bubblers!
Informing you that this plugin has been updated with Conversation Audio Recording capabilities.
Enjoy!
Hey guys,
The latest update supercharge your app by letting OpenAI Realtime API automatically pull relevant data from your app database with respect to privacy rules to enhance responses (RAG, a.k.a Retrieval-Augmented Generation). No more manual searching—just seamless AI-powered insights!
Step 1: Set App Data Retrieval on the element
Step 2: Enable your App Data API for the desired fields
!
That’s it! OpenAI Realtime API will now pull real-time data from your app whenever needed—making responses smarter, faster, and more accurate.
Remember: Set up your privacy rules to keep everything secure!
Let me know if you have any issues.
Enjoy!
Would it be possible to give the customer options to choose which voice (female or male) and which tone of voice will be applied in conversations?
OpenAI provides male/female voice type through the voice name parameter.
Regarding the tone, the best is to pass it through the instructions or prompt.
Dear Bubblers!
Just to let you know that the plugin has been updated to allow you to select the input transcription model and language to get a more accurate transcription results.
Enjoy!