The choice is stored only in a first-party preference cookie on this site.
Login
PUBLIC SOFTWARE / HANGRY LABS
Tools built to runclose to home.
Open software for voice, speech, and local AI operations, packaged for real hardware, honest about trade-offs, and ready to explore.
PROJECT GALLERY
Pick a tool. See what it does.
Choose a project image to reveal a compact guide directly below it. Select it again to close.
Local song generation
YuE2
Generate songs locally from lyrics and musical direction, with stereo 48 kHz output, editable ABC scores, a browser library, replayable takes, and native HTTP jobs.
Download both GGUF models into data/models first; follow the installation guide before running this command.
Linux / Bash
docker run -d --name yue2 --restart unless-stopped --gpus all -p 127.0.0.1:8087:8087 --mount "type=bind,source=$(pwd)/data/models,target=/models,readonly" -v yue2-output:/output hangrylabs/yue2:latest
Windows PowerShell
docker run -d --name yue2 --restart unless-stopped --gpus all -p 127.0.0.1:8087:8087 --mount "type=bind,source=$($PWD.Path)\data\models,target=/models,readonly" -v yue2-output:/output hangrylabs/yue2:latest
Restore single-speaker audio, split a two-speaker mixture, enhance both tracks, or convert formats without loading a model, using one local studio and audio-job APIs.
First command
docker run -d --name sidon --restart unless-stopped -p 127.0.0.1:7868:7868 --gpus all -v sidon_data:/app/persistent hangrylabs/sidon:latest
A local-first 82M-parameter TTS workspace with 173 voices across 11 languages, five independently managed model packs, streaming, SSML dialogue, OpenAI-compatible APIs, and opt-in MCP tools.
First command
docker run -d --name kokorotts --restart unless-stopped -p 127.0.0.1:7860:7860 --gpus all -v kokorotts_data:/app/persistent hangrylabs/kokorotts:latest
A local TTS workspace with eight models across six languages, a responsive browser UI, OpenAI-compatible and native APIs, six output formats, and sentence-streamed MP3/PCM.
First command
docker run -d --name melotts --restart unless-stopped -p 127.0.0.1:8888:8888 --gpus all -v melotts_data:/app/persistent hangrylabs/melotts:latest
A local voice studio for 600+ languages with voice design, microphone and reference cloning, reusable profiles, SSML-H dialogue, streaming, and OpenAI-compatible APIs.
First command
docker run -d --name omnivoicetts --restart unless-stopped -p 127.0.0.1:7861:7861 --gpus all -e CUDA_VISIBLE_DEVICES=0 -v omnivoicetts_data:/app/persistent hangrylabs/omnivoicetts:latest
A local Qwen3-TTS workspace for voice design, consented reference cloning, built-in speakers, multilingual streaming, SSML-H dialogue, reusable voices and scripts, and OpenAI-compatible applications.
First command
docker run -d --name faster-qwen3-tts-studio --restart unless-stopped -p 127.0.0.1:7860:7860 --gpus all -e CUDA_VISIBLE_DEVICES=0 -v faster_qwen3_tts_studio_data:/app/persistent hangrylabs/faster-qwen3-tts-studio:latest
A local VoxCPM2 workspace for 30-language generation, voice design, reference and transcript-guided cloning, reusable profiles, progressive MP3 streaming, and HTTP APIs.
First command
docker run -d --name voxcpmtts --restart unless-stopped -p 127.0.0.1:8808:8808 --gpus all -e CUDA_VISIBLE_DEVICES=0 -v voxcpmtts_data:/app/persistent hangrylabs/voxcpmtts:latest
A current local ASR service for 30-language transcription, bounded live microphone sessions, exact timestamps and subtitles, OpenAI-compatible clients, and opt-in MCP transcription from local files or URLs.
First command
docker run -d --name qwen3-asr-stt --restart unless-stopped -p 127.0.0.1:8000:8000 --gpus all -e CUDA_VISIBLE_DEVICES=0 -v qwen3_asr_stt_data:/app/persistent hangrylabs/qwen3-asr-stt:latest