Kana & Mari

Kana & Mari's SoundRepos (Japanese)

Technology JA ↓ 101 episodes

※この番組は日本語でお届けします。 Kana と Mari が、GitHub で見つけた TTS・MIDI・Audio など “音” にまつわる注目リポジトリを声で紹介。音とコードが交差するオープンソースの世界を軽やかにナビゲートします。 Kana と Mari のプロフィールはこちら： Kana – Newbie Esports Caster Mari – Newbie Esports Analyst ※ 本番組の原稿は生成 AI を用いて自動生成されています。内容には誤りを含む可能性がありますので参考情報としてお楽しみください。

Author

Kana & Mari

Episodes

maum-ai/univnet 27.04.2026 1:36

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

LSimon95/megatts2 26.04.2026 1:40

Unoffical implementation of Megatts2

makerjackie/MTTS 25.04.2026 1:44

A Demo of Mandarin/Chinese TTS frontend

haoheliu/voicefixer_main 24.04.2026 1:42

General Speech Restoration

ManimCommunity/manim-voiceover 23.04.2026 1:38

Manim plugin for all things voiceover

travisvn/obsidian-edge-tts 22.04.2026 1:51

Free, high quality text-to-speech for your Obsidian notes, leveraging Microsoft Edge's Read Aloud API.

zlargon/google-tts 21.04.2026 1:31

Google TTS (Text-To-Speech) for node.js

developersdigest/ai-devices 20.04.2026 1:47

AI Device Template Featuring Whisper, TTS, Groq, Llama3, OpenAI and more

zarazhangrui/personalized-podcast 19.04.2026 1:29

Turn any content into a personalized AI podcast. NotebookLM-style, except you control the script, voices, and hosts. Listen in Apple Podcasts, Spotify, or any podcast app.

debpalash/OmniVoice-Studio 18.04.2026 1:44

A Cinematic audio dubbing, Cloning and voice generation studio

akdeb/ElatoAI 17.04.2026 2:00

Realtime Voice AI with 100+ Models on Arduino ESP32 for AI Toys, Companions, and Devices

izwi-ai/izwi 16.04.2026 1:37

Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.

moonshine-ai/moonshine 15.04.2026 1:37

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

Saganaki22/ComfyUI-OmniVoice-TTS 14.04.2026 1:43

OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning, voice design, and multi-speaker dialogue

OpenMOSS/MOSS-TTS-Nano 13.04.2026 1:47

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving, and lightweight product integration.

Aratako/T5Gemma-TTS 12.04.2026 1:48

Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM

lmnt-com/wavegrad 11.04.2026 1:38

A fast, high-quality neural vocoder.

mbzuai-oryx/LLMVoX 10.04.2026 2:01

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Adri6336/gpt-voice-conversation-chatbot 09.04.2026 1:48

Allows you to have an engaging and safely emotive spoken / CLI conversation with the AI ChatGPT / GPT-4 while giving you the option to let it remember things discussed.

richardr1126/openreader 08.04.2026 1:59

An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and MD.

Aratako/Irodori-TTS 07.04.2026 1:45

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

LlmKira/fast-langdetect 06.04.2026 1:44

⚡️ 80x faster Fasttext language detection out of the box | Split text by language

Sharrnah/whispering-ui 05.04.2026 1:38

Native UI for the Whispering Tiger project - https://github.com/Sharrnah/whispering (live transcription / translation)

keonlee9420/Expressive-FastSpeech2 04.04.2026 1:42

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

Agents365-ai/video-podcast-maker 03.04.2026 1:48

AI-powered video podcast creation skill for coding agents. Supports Bilibili & YouTube, multi-language (zh-CN/en-US), 6 TTS engines (Edge/Azure/ElevenLabs/OpenAI/Doubao/CosyVoice), 4K Remotion rendering.