Promote Sign in Sign up

Catalogs

Models

372 matched .

Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.

Clear search and filters

All types Text · 2,080 Image · 398 Video · 224 Audio · 372 Coding · 40 Multimodal · 885 Structured data · 27 3D · 17
Weights and source
Open weights Closed On Hugging Face Clear filters
Most downloaded A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose models

Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.

Understand our sources and data limits

  1. MOSS TTS Nano OpenMOSS MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and OpenMOSS… Audio · Open weights 108k HF downloads
  2. Zonos-v0.1-transformer Zyphra text to speech · License apache-2.0 · 107,508 downloads · by Zyphra Audio · Open weights 108k HF downloads
  3. faster-whisper-medium.en Systran automatic speech recognition · License mit · 106,988 downloads · by Systran Audio · Open weights 107k HF downloads
  4. diar_sortformer_4spk-v1 nvidia automatic speech recognition · License cc-by-nc-4.0 · 105,422 downloads · by nvidia Audio · Open weights 105k HF downloads
  5. s2t-small-librispeech-asr facebook automatic speech recognition · License mit · 104,863 downloads · by facebook Audio · Open weights 105k HF downloads
  6. react-native-executorch-kokoro software-mansion text to speech · License apache-2.0 · 101,598 downloads · by software-mansion Audio · Open weights 102k HF downloads
  7. higgs-tts-3-4b bosonai text to speech · License other · 101,389 downloads · by bosonai Audio · Open weights 101k HF downloads
  8. uzbek-stt-3 sarahai automatic speech recognition · License apache-2.0 · 100,707 downloads · by sarahai Audio · Open weights 101k HF downloads
  9. Voxtral-Small-24B-2507-gguf handy-computer automatic speech recognition · License apache-2.0 · 96,442 downloads · by handy-computer Audio · Open weights 96k HF downloads
  10. whisper-small.en openai automatic speech recognition · License apache-2.0 · 95,649 downloads · by openai Audio · Open weights 96k HF downloads
  11. whisper-base onnx-community automatic speech recognition · 93,534 downloads · by onnx-community Audio · Open weights 94k HF downloads
  12. wav2vec2-large-xlsr-53-german jonatasgrosman automatic speech recognition · License apache-2.0 · 92,730 downloads · by jonatasgrosman Audio · Open weights 93k HF downloads
  13. canary-1b-v2-gguf handy-computer automatic speech recognition · License cc-by-4.0 · 91,856 downloads · by handy-computer Audio · Open weights 92k HF downloads
  14. speecht5_asr microsoft automatic speech recognition · License mit · 90,039 downloads · by microsoft Audio · Open weights 9k HF downloads
  15. TIGER-DnR JusperLee audio to audio · License apache-2.0 · 89,213 downloads · by JusperLee Audio · Open weights 89k HF downloads
  16. musicgen-large facebook text to audio · License cc-by-nc-4.0 · 88,637 downloads · by facebook Audio · Open weights 89k HF downloads
  17. react-native-executorch-whisper-tiny.en software-mansion automatic speech recognition · License apache-2.0 · 85,946 downloads · by software-mansion Audio · Open weights 86k HF downloads
  18. MOSS TTS Local Transformer v1.5 OpenMOSS MOSS-TTS-Local-Transformer-v1.5 is a 5B-parameter text-to-speech model supporting 31 languages with… Audio · Open weights 86k HF downloads
  19. Fun-ASR-Nano-2512-hf FunAudioLLM automatic speech recognition · License apache-2.0 · 85,442 downloads · by FunAudioLLM Audio · Open weights 85k HF downloads
  20. ASR-Somali Mustafaa4a automatic speech recognition · License apache-2.0 · 81,555 downloads · by Mustafaa4a Audio · Open weights 82k HF downloads
  21. Cohere Transcribe Arabic Cohere Cohere Transcribe Arabic is a 2B parameter conformer based encoder decoder automatic speech recogni… Audio · Open weights 44k HF downloads
  22. Canary 1B v2 NVIDIA Multilingual, multitask speech recognition model (ASR) in the NVIDIA NeMo family. Audio · Open weights 39k HF downloads
  23. Suno Bark Suno Suno Bark is an open-source text-to-audio model that generates expressive speech—and even music, ef… Audio · Closed 31k HF downloads
  24. Dia 1.6B Nari Labs Dia-1.6B is Nari Labs’ ultra-compact instruction model—about 1.6B parameters—built for fast, low-co… Audio · Open weights 29k HF downloads
  25. Stable Audio Open Stability AI Stable Audio Open is Stability AI's open text-to-audio model for sound effects, samples and product… Audio · Closed 2k HF downloads
  26. SAM Audio Meta Platforms SAM Audio is Meta’s Segment Anything audio model, a unified system that segments sounds from comple… Audio · Open weights 14k HF downloads
  27. Magenta RealTime 2 Google DeepMind Magenta RealTime 2 is Google DeepMind’s open on-device live music-generation model for low-latency,… Audio · Closed 8.6k HF downloads
  28. TADA 1B Hume AI TADA-1B is a unified speech-language model checkpoint that aligns text tokens and speech representa… Audio · Open weights 7.5k HF downloads
  29. Maya1 Maya Research Maya1 is a compact general model for reasoning, writing, and code. It offers long context, reliable… Audio · Closed 7.3k HF downloads
  30. Music Flamingo NVIDIA Music Flamingo is NVIDIA’s large audio-language model for deep music understanding, fine-tuned on t… Audio · Closed 6.9k HF downloads
  31. LuxTTS ysharma3501 ZipVoice-based voice cloning TTS that generates 48 kHz speech at up to 150x real time, fitting in a… Audio · Open weights 6.2k HF downloads
  32. Step-Audio-EditX StepFun Step-Audio-EditX is a text-guided audio editor for speech, music, and effects. Describe the change… Audio · Open weights 4.1k HF downloads
  33. AuK Tencent AuK is a 1.5 billion parameter open source speech foundation model that generates and edits speech… Audio · Open weights 3k HF downloads
  34. Canary 180m flash NVIDIA Canary 180M Flash is a compact automatic speech recognition model in NVIDIA’s Canary family, design… Audio · Open weights 3k HF downloads
  35. SoulX FlashTalk Soul AILab SoulX-FlashTalk is a 14B audio-driven avatar model that delivers high-fidelity lip-synced digital h… Audio · Closed 2.7k HF downloads
  36. Chatterbox Multilingual Resemble AI AI model by Resemble AI Audio · Closed 2.3k HF downloads