Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Sophon-Realtime-v1
Modelsany to any model by adventists-ai
adventists-ai/Sophon-Realtime-v1 -
moe-speech
Datasets & benchmarksHugging Face dataset by litagin
litagin/moe-speech -
segmentation
Modelsvoice activity detection model by pyannote · pyannote-audio
pyannote/segmentation -
ultravox
AI repositoriesA fast multimodal LLM for real-time voice
git clone https://github.com/fixie-ai/ultravox.git -
airline-customersupport-Hinglish-audio
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/airline-customersupport-Hinglish-audio -
e-commerce-customersupport-english-audio
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/e-commerce-customersupport-english-audio -
Audio8-TTS-Realistic-Air
Modelstext to speech model by Edge0 · transformers
Edge0/Audio8-TTS-Realistic-Air -
GLM-TTS
Modelstext to speech model by zai-org · glm-tts
zai-org/GLM-TTS -
MiniCPM-o-2_6
Modelsany to any model by openbmb · transformers
openbmb/MiniCPM-o-2_6 -
tiny-voca
Modelstext to speech model by n4ze3m
n4ze3m/tiny-voca -
gemma-3n-E4B-it
Modelsimage text to text model by google · transformers
google/gemma-3n-E4B-it -
Ming-3.0-tts-0.5B
Modelstext to speech model by inclusionAI · transformers
inclusionAI/Ming-3.0-tts-0.5B -
dissect
SkillsReverse-engineer any video (YouTube, TikTok, Reels, X...) into a reusable blueprint for making similar videos. A Claude Code skill.
git clone https://github.com/0xpratzyy/dissect.git -
Dramabox
Modelstext to speech model by ResembleAI · ltx-audio-tts
ResembleAI/Dramabox -
Amazon Connect Contact Lens
Public APIsContact Lens for Amazon Connect enables you to analyze conversations between customer and agents, by using speech transcription, natural language processing, and intelligent search capabilities. It performs sentiment analysis, detects issues, and enables you to automatically categorize contacts. Contact Lens for Amazon Connect provides both real-time and post-call analytics of customer-agent…
-
automatic speech recognition model by ibm-granite · transformers
ibm-granite/granite-speech-5.0-470m-turboctc -
granite-speech-5.0-2b
Modelsautomatic speech recognition model by ibm-granite · transformers
ibm-granite/granite-speech-5.0-2b -
Qwen3-TTS-12Hz-0.6B-Base
Modelstext to speech model by Qwen
Qwen/Qwen3-TTS-12Hz-0.6B-Base -
Bert-VITS2
AI repositoriesvits2 backbone with multilingual-bert
git clone https://github.com/fishaudio/Bert-VITS2.git -
MoneyPrinterTurbo
AI repositories利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
git clone https://github.com/harry0703/MoneyPrinterTurbo.git -
Chroma-4B
Modelsany to any model by FlashLabs · transformers
FlashLabs/Chroma-4B -
LFM2.5-Audio-1.5B
Modelsaudio to audio model by LiquidAI · liquid-audio
LiquidAI/LFM2.5-Audio-1.5B -
Audio8-TTS-Preview-0.6b
Modelstext to speech model by Edge0 · transformers
Edge0/Audio8-TTS-Preview-0.6b -
ODS
Agents & frameworksODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
git clone https://github.com/Osmantic/ODS.git
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.