/Tech20d ago

Gradium TTS Transfers Reverb And Bandwidth For Realistic AI Voices

3549499.7K

#987

Original post

Matt Turck#987

Neil Zeghidour@neilzegh

Gradium TTS is particularly good at transferring all characteristics including reverb, bandwidth (e.g. phone speech), even typical podcast mic saturation on plosives ("p" sound). All samples in the video just generated from 10 samples without any processing.

@levelsio@levelsio

I'm just as surprised nobody in AI voice tech has realized a voice needs background and environmental noise to sound realistic

Even @ElevenLabs the leader in voice AI can not produce voice with background noise, or environment reverb sound

AI voices are always going to sound non-passable as human if they don't have that

And it's only me and this other guy even talking about it

2:38 PM · May 25, 2026 · 9.7K Views

Sentiment

Positive users express excitement that Gradium TTS could solve AI voice problems, while negative users find the API's limit on voice cloning frustrating.

Pos

50.0%

Neg

50.0%

2 comments with sentiment.

Cluster Engagement

Posts from X

Most Activity

Asym@Asym_Alwali

@neilzegh Wow seems it wio solve that ai voice problems.

20d26

s______-O🏳️‍🌈@milkteapuff

@neilzegh I don’t get it. As a developer, I found it limiting the voice clone to 5 frustrating, why can’t the API support create an TTS with audio and text as input? Why do we need to clone the voice first?

20d7