Feature Request: Advanced Text-to-Speech Customization
I would love to see ChatGPT introduce an advanced Text-to-Speech (TTS) customization feature as soon as possible.
Users should be able to adjust speech speed, pitch, voice tone, pronunciation, and emotional expression through a dedicated settings panel.
I would also like the ability to select text and have ChatGPT read only that specific section aloud.
Please consider adding customizable speech settings with adjustable speed (0.5x-3x), pitch control, voice selection, and saved voice presets.
This feature would significantly improve accessibility, personalization, and the overall ChatGPT experience.
I hope the OpenAI team considers prioritizing this feature in a future update.