SOURCE-REVIEWED MODEL PROFILE
Kokoro-82M
A lightweight text-to-speech model with Apache-licensed weights for local speech synthesis.
Metadata reviewed 2026-10-24 · Original creator: hexgrad
What it does
- Local speech synthesis
- External task-specific runtime; not integrated into launcher chat
Local fit
Very small model / edge candidate; runtime validation required. Requires a dedicated Kokoro audio runtime and its voice assets. Built-in launcher chat does not synthesize speech.
Runtime limits and on-device memory must be validated separately.
Evidence and limits
Source reviewed only. No local model or Android inference test performed.
External task-specific runtime; not integrated into launcher chat
License and source
Review the exact checkpoint, voice assets and applicable upstream notices; model references do not grant new rights.
Read the original model card ↗
Reviewed source revision: f3ff3571791e39611d31c381e3a41a3af07b4987