A speech.cpp‑only GGUF model for Japanese TTS that delivers single‑sentence audio in a reference voice or a described/auto‑chosen voice, using Euler sampling (default 40 steps) and supporting custom guidance, schedule, and speaker scaling.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
4,000
Hugging Face likes
1
Listed
Oct 27, 2026
Popular in the same category
- piper-plus-tsukuyomi-chanayousanz4kA Japanese TTS model named tsukuyomi‑wavlm—fine‑tuned for 300 epochs on 100 utterances from the tsukuyomi corpus, using the WavLM discriminator and A1/A2/A3 prosody features on a VITS architecture, exported as a 61 MB ONNX file that generates 22.05 kHz syntheses.
- sarashina2.2-ttssbintuitions3kA Japanese‑centric, bilingual text‑to‑speech system built on a large language model that delivers highly accurate, natural, and stable pronunciation for both Japanese and English—including mixed code‑switching—and supports zero‑shot voice cloning across diverse speaking styles with responsibly sourced training data.
- irodori-tts-GGUFcstr1kIrodori‑TTS‑500M‑v3 is a 500 M‑parameter Rectified Flow Diffusion Transformer for Japanese/mixed text, released as GGUF/ggml quantised models (F16 ≈1.9 GB, Q4_K ≈852 MB, Q8_0 ≈896 MB) with an optional reference‑latent encoder and semantic DAC‑VAE decoder, licensed under MIT.
- Drama-3-JapaneseAratako1kJapanese fine‑tuned Fish Audio Drama 3 model enabling single‑speaker text‑to‑speech with optional reference audio, descriptive captions, and inline emotion tags for expressive delivery.
- Irodori-TTS-v4.1-Small-MF-CoreMLAILogDev1kA Core ML model and Swift SDK for Japanese TTS on iPhone/Apple‑Silicon Mac that supports full‑size and lightweight INT8 versions, voice cloning, text‑driven speaking style, offline synthesis to 48 kHz mono PCM16 WAV, with easy download, verification, and sample projects.
Resources in similar research fields
GPT-SoVITSRVC-Boss62k1 min voice data can also be used to train a good TTS model! (few shot voice cloning)MultilingualShared: Speech synthesis
barksuno-ai39k🔊 Text-Prompted Generative Audio Model.MultilingualShared: Speech synthesis
VoxCPMOpenBMB38kVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.MultilingualShared: Speech synthesis
OpenVoicemyshell-ai38kInstant voice cloning by MIT and MyShell. Audio foundation model.MultilingualShared: Speech synthesis
fish-speechfishaudio33kSOTA Open Source TTS.MultilingualShared: Speech synthesis
chatterboxresemble-ai27kSoTA open-source TTS.MultilingualShared: Speech synthesis