CoolFace
Apppublic

akshan-main/glossolalia

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
1likes
App README

Glossolalia Dial

Glossolalia Dial is a text-to-speech toy with one knob. Type a sentence and it speaks it. Turn the knob up and the words come apart into wordless babble that still sounds like a language, in the same voice the whole way. The trick is the middle, where the sentence is half-dissolved instead of cutting straight from speech to noise.

Demo video: https://youtu.be/dDOaBNfihyo

Two modes

  • —Tongues is the words slurring into made-up pseudo-words. A LoRA and a learned dial trained into F5-TTS. This is the glossolalia.
  • —Ghost swaps every word for a real one that sounds close (seashells becomes seagulls), the misheard-lyric thing. Pareidolia, not glossolalia, and labeled so. No model, runs live.

Use it

Type a sentence, pick a voice (nine presets or clone your own from a short clip), turn the dial 0 to 4, and hit play. Hit dissolve to hear the whole sweep in one take. You can also mix in a backing track, hand-tune any word, or wrap it in reverb.

How it works

There's no dataset of sentences falling apart into nonsense, so it builds one: corrupt each sentence's phonemes at five rising rates, have base F5-TTS read each, then train the dial to reproduce that slide from the clean sentence alone. The model never sees the corrupted text, it learns the slide from the dial. Ghost mode trains nothing, it searches CMUdict for close-sounding words live and reranks them with DistilGPT-2.

The corruption is built to sit inside real glossolalia's structure, not just noise: it only swaps within the English phoneme inventory (speakers reuse their native phonotactics, Samarin 1972, Goodman 1972) and keeps syllable count and stress while leaning toward open CV syllables (measured at 95.7% in glossolalic speech, Link & Tomaschek 2024). The exact sound palette is a taste choice, not a claim to match the distribution.

Models (all local, all under 32B)

ModelSizeRole
F5-TTS v1 Base~336Mthe voice (flow-matching TTS, zero-shot clone)
Glossolalia LoRArank-16the dial
DistilGPT-2~82MGhost-mode word reranking
Whisper base.en~74Mclone-reference transcription

No cloud APIs. Everything runs on the Space.

Badges

  • —🎯 Well-Tuned: the fine-tuned LoRA, published at `akshan-main/glossolalia-dial-lora`.
  • —🔌 Off the Grid: no cloud APIs, zero cloud SDKs in requirements.txt.
  • —🎨 Off-Brand: the dial is a hand-built circular knob, not a default slider.
  • —📓 Field Notes: the writeup is linked below.

Links

  • —Demo video: https://youtu.be/dDOaBNfihyo
  • —Writeup: https://x.com/frutigeraerosol/status/2066667649338417367
  • —Model (LoRA): https://huggingface.co/akshan-main/glossolalia-dial-lora
  • —Dataset: https://huggingface.co/datasets/akshan-main/glossolalia-inputs
  • —Code: https://github.com/akshan-main/glossolalia