Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for builders who want local text-to-speech that fits on modest GPUs instead of treating TTS as a multi-gigabyte sidecar.
Who should use it
Who should skip it
Move on from kizuna-intelligence/Irodori-TTS-Lite if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
kizuna-intelligence/Irodori-TTS-Lite is tracked by RepoRadar as a model / inference in the Inference / Voice section. It was first seen on 2026-07-01 and last updated on 2026-07-01. The current verdict is 'worth watch' with a Silver tier and advanced setup difficulty. Across RepoRadar's eight signals, kizuna-intelligence/Irodori-TTS-Lite is strongest on open-source/build quality (8.4) and workflow potential (8.2) and weakest on setup ease (4.2) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned kizuna-intelligence/Irodori-TTS-Lite a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read Local AI vs. hosted APIs: how to choose for the checklist behind this score.
Risk explanation
It is a voice-generation runtime, so first evaluation should stay with voices and content you have the rights and consent to synthesize; The published memory and latency numbers come from a specific GPU setup and the documentation is mostly Japanese, so verify the claims on your own hardware before treating the benchmark table as portable.