Pinned Repositories
F5-TTS
Fork for PRs for F5-TTS. See branches for latest work
gpus
GPUs go brrr
openbridge
Use Claude Code with any LLM provider - GLM-4.5, Kimi-K2, Qwen3-Coder, DeepSeek, etc.
OpenF5-TTS
(WIP) A retrain of F5-TTS on permissively-licensed data
simpletts
A lightweight Python library for running TTS models with a unified API.
ttstune
WIP • Untested • Not ready yet
txtsplit
A simple text splitter based on Tortoise for use in text-to-speech applications
utmos
A toolkit to calculate speech audio quality. Not affiliated with the original authors
OpenPhonemizer
An espeak-compatible, permissively-licensed IPA phonemizer (G2P) based on DeepPhonemizer. Usable as a drop-in replacement for espeak's GPL phonemizer.
VibeVoice
VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)
fakerybakery's Repositories
fakerybakery/openbridge
Use Claude Code with any LLM provider - GLM-4.5, Kimi-K2, Qwen3-Coder, DeepSeek, etc.
fakerybakery/simpletts
A lightweight Python library for running TTS models with a unified API.
fakerybakery/OpenF5-TTS
(WIP) A retrain of F5-TTS on permissively-licensed data
fakerybakery/gpus
GPUs go brrr
fakerybakery/ttstune
WIP • Untested • Not ready yet
fakerybakery/F5-TTS
Fork for PRs for F5-TTS. See branches for latest work
fakerybakery/ACE-Step
`pip`-installable fork of ACE-Step
fakerybakery/better-chatterbox
My fork of Chatterbox with some experimental features. ** HIGHLY UNSTABLE **
fakerybakery/dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
fakerybakery/hfapi
Unofficial Python SDK for all Hugging Face API methods - not just the ones included in huggingface_hub.
fakerybakery/magenta-realtime
fakerybakery/MegaTTS3-Voice-Cloning
fakerybakery/openf5-utils
fakerybakery/sonique
Video Background Music Generation Using Unpaired Audio-Visual Data
fakerybakery/star-vector
StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.
fakerybakery/accessible-llm-tts-ui
Don't rely on it
fakerybakery/axolotl
Go ahead and axolotl questions
fakerybakery/diffrhythmp
fakerybakery/easym4b
High-performance M4B chapter splitter.
fakerybakery/emotion-annotations
See the branches
fakerybakery/fakerybakery
Config files for my GitHub profile.
fakerybakery/hf-tools
Browser extension w/ some additional functionality for Hugging Face Hub
fakerybakery/kif
mirror of https://code.google.com/archive/p/adqmisc/
fakerybakery/librivox-catalog
LibriVox catalog and reader workflow application
fakerybakery/llamafy-apriel
fakerybakery/mochi-preview-zerogpu
The best OSS video generation models
fakerybakery/MoonCast
fakerybakery/ttslab
Still a very early WIP
fakerybakery/vocos
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
fakerybakery/VoiceStar
`pip`-installable, MPS-compatible fork of VoiceStar