Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
VibeVoice-Realtime-0.5B
Modelstext to speech model by microsoft · transformers
microsoft/VibeVoice-Realtime-0.5B -
maya2-native
Modelstext to speech model by maya-research
maya-research/maya2-native -
Audio8-ASR-Infinite
Modelsautomatic speech recognition model by Edge0 · transformers
Edge0/Audio8-ASR-Infinite -
Mage-VL
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL -
phonon-31m-en
Modelstext to speech model by gradium · transformers
gradium/phonon-31m-en -
phonon-40m-en
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-en -
phonon-40m-multilingual
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-multilingual -
phonon-40m-fr
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-fr -
phonon-40m-es
Modelstext to speech model by gradium · transformers
gradium/phonon-40m-es -
Silencio-2
Modelstext to speech model by BlueRoseLabs · pytorch
BlueRoseLabs/Silencio-2 -
SOV-Transcribe-1
Modelsautomatic speech recognition model by salesforce-sovereign-intelligence · transformers
salesforce-sovereign-intelligence/SOV-Transcribe-1 -
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-speech-streaming-en-0.6b -
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-3.5-asr-streaming-0.6b -
Meta: Muse Wonder
ModelsMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
meta/muse-wonder -
Perceptron: Perceptron Mk1.5
ModelsPerceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...
perceptron/perceptron-mk1.5 -
Amazon: Nova 2 Lite
ModelsNova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
amazon/nova-2-lite-v1 -
Google: Gemini 4 Carbon
ModelsGemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...
google/gemini-4-carbon -
Anthropic: Claude Fable 5
ModelsClaude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
anthropic/claude-fable-5 -
Reka Edge
ModelsReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
rekaai/reka-edge -
Qwen: Qwen4 Max
ModelsQwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....
qwen/qwen4-max -
Meta: Muse Spark 1.2
ModelsMuse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....
meta/muse-spark-1.2 -
Meta: Muse Spark 1.1
ModelsMuse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....
meta/muse-spark-1.1 -
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...
google/gemini-4-carbon:batch -
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
anthropic/claude-fable-5:batch
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.