Feature Requests

Hi, Hume team! I hope you're well. Is there any way you could directly support ChatGPT-4o-latest for EVI 2? The only way to currently use that supplemental LLM is to set up a CLM which, as mentioned in your docs, increases latency.

Octave voices are currently only supported for Hume's Text-To-Speech API . Soon, we plan to add support for Octave voices to the Empathic Voice Interface , so you will be able to use them in conversations with users. Follow this post for updates!

Thanks

This is a feature request to add programmatic playback volume control to the @humeai/voice-react SDK. Currently, users can only mute or unmute the audio output. The proposal is to expose controls via the useVoice hook, specifically adding a volume state (ranging 0.0-1.0) and a setVolume(level) function. This enhancement would allow developers to synchronize the EVI volume with their application's own sound controls for a more integrated user experience.

Dedicated API endpoint to generate EVI-like voice from text

i can't get it to slow down the pace with the acting instructions or with .... so some type of markup would be nice to specify number of seconds

Currently, I can't find an option to rename a voice I created.

Ability to design personalized characters within the app (iOS and app.hume.ai ) by customizing various attributes, including but not limited to: prompt, voice, LLM

i created a voice and after refreshing the text to speach project i was working on, the voice is gone.