AI/ML●●●Banger
Real-time local TTS (31M params, 5.6x CPU, voice cloning, ONNX)
5.6x realtime on CPU with voice cloning beats most local TTS options.
WizardryDark Horse
ZDisket
444mo ago
Back to browse
Inflect TTS v2+ONNX, 9M/4M text-to-speech models running in the browser
by g58892881·Jul 26, 2026·3 points·2 comments
AI Analysis
●MidSlick
ONNX Runtime Web integration is clean, but browser TTS demos are becoming common.
Strengths
- •Tiny 4M parameter model enables fast loading and low bandwidth usage.
- •Complete client-side execution ensures no audio data leaves the user's browser.
Weaknesses
- •Lacks unique features beyond basic generation found in many similar browser demos.
- •No apparent offline support or PWA capabilities despite the local execution model.
Category
Target Audience
Web developers needing privacy-focused audio generation
Similar To
ElevenLabs · Bark · Coqui TTS
Similar Projects
AI/ML●●●Banger
Pocket Voice: TTS and Voice clone in the browser
Runs voice cloning entirely client-side via ONNX when every competitor requires a server.
Zero to OneWizardrySolve My Problem
init0
309d ago
AI/ML●●Solid
Three new models by KittenML. <25 MB Open-source TTS. Highly Expressive
Sub-25MB TTS models when Coqui and glow-TTS already dominate the space.
Niche GemShip It
rohan_joshi
465mo ago
AI/ML●●●Banger
Pocket TTS running in (mobile) Safari
100M param TTS streaming in mobile Safari when cloud APIs dominate.
WizardryZero to OneNiche Gem
ldenoue
102mo ago
AI/ML●Mid
TTS Model – Another attempt to cross the uncanny valley
Another TTS API at $2.40/hr competing with ElevenLabs and PlayHT.
Ship It
cyrus_ck
2223d ago
AI/ML●●●Banger
Three new Kitten TTS models – smallest less than 25MB
SOTA expressivity at 14M parameters beats cloud models for on-device TTS.
WizardryNiche GemZero to One
rohan_joshi
5611814mo ago