Show HN: Nano-Edge-TTS – 70x realtime, Lightweight Kokoro-based TTS model
drmhse
13 points
3 comments
November 15, 2026
Related Discussions
Found 5 related stories in 144.9ms across 12,728 title embeddings via pgvector HNSW
- Show HN: OfflineTTS — Free browser-based TTS & STT that runs locally twainyoung · 11 pts · July 19, 2026 · 64% similar
- Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost toebee · 75 pts · September 14, 2026 · 63% similar
- Show HN: Orate – On-device neural text-to-speech queue for Mac bherms · 11 pts · July 21, 2026 · 63% similar
- How we made a text-to-speech model respond in sub-50 ms toebee · 129 pts · August 21, 2026 · 62% similar
- Show HN: 1667, a terminal UI for writing fiction with language models refsab · 35 pts · August 17, 2026 · 59% similar
Discussion Highlights (3 comments)
pikann22
This is awesome! I'm currently using Kokoro in my open-source English learning app ( https://github.com/pikann/engclaw ) Since it runs locally on the user's machine, the model footprint takes up quite a bit of disk space This model is exactly what I've been looking for!
carter-qadenza
I gotta try this. We were looking into Kokoro for TTS but in an effort to keep the application small we decided to cut it for now. Maybe I can get it working after all! ;)
anilgulecha
Is this small enough to run on browser just a simple runtime that's downloaded/intiialized? also on CPU only edge nodes?