Dear OpenAI Team,
I am writing to report an issue I encountered while using ChatGPT with GPT 4o-mini. When I submit a very long translation request and ask the model to continue generating the text, I notice that the voice synthesis feature only reads the second part of the generated text. This seems to be a bug, as the voice synthesis should read the entire message.
Here is a step-by-step description of the issue:
I submit a very long translation request to ChatGPT.
I ask the model to continue generating the text.
Once the text generation is complete, I initiate the voice synthesis feature to read the text aloud.
The voice synthesis only reads the second part of the generated text, ignoring the first part.
This issue disrupts the continuity of the text and makes it difficult to follow the complete translation. I believe this is a bug that needs to be addressed to ensure a seamless user experience.
Thank you for your attention to this matter. I look forward to a resolution.
Best regards,
SAM