Ninada v5.1.0 open-sources multilingual browser TTS
Developer Hemanth announced the open-source release of Ninada v5.1.0, with MIT-licensed code and 48 CC-BY-4.0 ONNX checkpoints for 24 kHz text-to-speech. The release covers Classical Sanskrit, English, and 10 Indic languages and includes a browser studio that runs locally without sign-up. The developer also reports phone WASM synthesis latency of 538–649 ms, while mobile WebGPU performed worse in their Pixel 10 Pro XL profiling.
Ninada provides open code, checkpoints, and local browser inference for multilingual TTS, including coverage for Classical Sanskrit and Indic languages.
Building an in-browser TTS model for Indic languages, including Classical Sanskrit, has been a longtime dream of mine. Today I'm open-sourcing Ninada (code MIT, 48 ONNX checkpoints CC-BY-4.0).
Live in-browser studio (zero sign-up, runs 100% locally): https://h3manth.com/ai/ninada/
Why I built it (and what broke on real phones)
Most open Indic TTS setups either rely on cloud APIs, ship multi-gigabyte unified checkpoints that bleed accents across scripts, or use 16 kHz Meta MMS VITS (1.5 GB across 12 languages, 5.17 dB MCD) exported as a monolithic ONNX graph that blocks until the entire sentence finishes.
When I profiled streaming VITS on a physical Pixel 10 Pro XL over wireless ADB, two common browser ML assumptions failed immediately: 1. Mobile WebGPU lost to WASM: Dawn shader compilation stalled cold start for 6 to 14 seconds, and GPU buffer readback pushed synthesis slower than real time (1.48x RTF). 2. 2-3 WASM threads ran slower than 1 thread: Heterogeneous big.LITTLE core scheduling stalled ONNX Runtime spin barriers (1.76x RTF at 2 threads vs 1.19x at 1 thread), only recovering at 4 threads.
#Ninada v5.1.0#ONNX Runtime#VITS#iSTFTNet#HiFi-GAN#WebGPU#WASM#Cascade Klatt-Akshara