Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-3.5-asr-streaming-0.6b -
bark
Modelstext to speech model by suno · transformers
suno/bark -
whistle
Modelsautomatic speech recognition model by Cactus-Compute · cactus-compute
Cactus-Compute/whistle -
OmniVoice
Modelstext to speech model by k2-fsa · omnivoice
k2-fsa/OmniVoice -
s2-pro
Modelstext to speech model by fishaudio
fishaudio/s2-pro -
seamless-m4t-v2-large
Modelsautomatic speech recognition model by facebook · transformers
facebook/seamless-m4t-v2-large -
ema-lightning
Modelstext to speech model by canberkkkkkk
canberkkkkkk/ema-lightning -
fastrtc
AI repositoriesThe python library for real-time communication
git clone https://github.com/gradio-app/fastrtc.git -
Verbatim Transcribe
MCP servers让 agent 驱动本机的 Verbatim 音视频转写与博主观点分析:提交转写、轮询、搜索转写库。
verbatim-transcribe-mcp@0.1.0 -
transcribe-mcp
MCP serversTranscribe audio/video and find dead air. Pay-per-call in USDC over x402 — no account, no key.
transcribe-mcp@0.1.1 -
bilibili-douyin-notes
Skills把 B站 / 抖音 / YouTube / 小红书视频一键整理成 Markdown 课堂笔记的 AI Agent Skill:字幕抓取 + 本地语音识别 + 笔记模板,免登录、不调付费 API
git clone https://github.com/lucky-Luor/bilibili-douyin-notes.git -
GPT-SoVITS
Modelstext to speech model by lj1995
lj1995/GPT-SoVITS -
Llasa-3B
Modelstext to speech model by HKUSTAudio
HKUSTAudio/Llasa-3B -
Confucius4-R2T2
Modelsautomatic speech recognition model by netease-youdao · transformers
netease-youdao/Confucius4-R2T2 -
supertonic
Modelstext to speech model by Supertone · supertonic
Supertone/supertonic -
Voxtral-4B-TTS-2603
Modelstext to speech model by mistralai · vllm
mistralai/Voxtral-4B-TTS-2603 -
seamless-m4t-large
Modelsautomatic speech recognition model by facebook · fairseq2
facebook/seamless-m4t-large -
Llama-3.1-8B-Omni
Modelsmodel by ICTNLP · llama-omni
ICTNLP/Llama-3.1-8B-Omni -
supertonic-2
Modelstext to speech model by Supertone · supertonic
Supertone/supertonic-2 -
MegaTTS3
Modelstext to speech model by ByteDance
ByteDance/MegaTTS3 -
VoxCPM1.5
Modelstext to speech model by openbmb · voxcpm
openbmb/VoxCPM1.5 -
orpheus-3b-0.1-ft
Modelstext to speech model by canopylabs · transformers
canopylabs/orpheus-3b-0.1-ft -
audio-video-transcriber
MCP serversTranscribe any audio or video URL to text, SRT and VTT, with chunking and only-new episodes
-
Name Whisper — ENS Intelligence Layer
MCP servers44 MCP tools to search, value, register, trade, and manage ENS names. AI-powered intelligence layer.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.