supertone-inc/supertonic

Health v2 · maintenance only

Adoption not part of the score

13734 stars · 1520 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Supertonic is a lightning-fast, on-device multilingual text-to-speech system powered by ONNX Runtime, with a compact 99M-parameter open-weight model supporting 31 languages. It runs locally on desktop, mobile, browsers, and edge hardware with no cloud dependency. Note: the repository is being archived with no further development or official support.

Use cases

• convert text to speech offline on device
• run fast tts on raspberry pi or edge hardware
• synthesize speech in multiple languages locally
• add text-to-speech to a mobile app without cloud api
• generate audio from webpages in under a second
• privacy-preserving speech synthesis with no api calls
• run tts in the browser via webgpu

When to choose

• you need low-latency, on-device tts with a small model footprint
• you want multilingual speech synthesis without cloud services
• you target resource-constrained or edge devices
• privacy rules forbid sending text to external apis

When to avoid

• you need ongoing official support or updates - the repo is archived as of July 2026
• you need voice cloning after August 2026 when Voice Builder shuts down
• you want the highest-quality large-model tts regardless of size
• you need a maintained, actively developed solution

Facets

library · maturity abandoned

tts speech-recognition machine-learning llm-inference speech-processing machine-learning cross-platform cross-platform python cpp rust go jvm browser wasm on-device-inference onnx-runtime speech-synthesis voice-cloning edge-devices multilingual-tts webgpu flutter natural-language-processing swift nodejs ios mobile desktop gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="supertone-inc/supertonic")