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. Rumik OSS 1 Rumik Rumik OSS 1 is an open source text to speech model built for Indic languages, generating expressive… Audio · Open weights 2k HF downloads
  2. Hibiki Zero Kyutai Real-time multilingual speech-to-speech translation model with voice transfer (selected languages i… Audio · Open weights 1.3k HF downloads
  3. LongCat AudioDiT 3.5B Meituan LongCat-AudioDiT-3.5B is Meituan LongCat’s diffusion-based text-to-speech model built directly in w… Audio · Open weights 1.2k HF downloads
  4. Fish Audio S2 Fish Audio Fish Audio S2 is Fish Audio’s latest text-to-speech model designed for natural, emotionally rich sp… Audio · Closed 977 HF downloads
  5. Supertonic Supertone Supertonic is Supertone’s lightning fast, on device text to speech system. It runs via ONNX Runtime… Audio · Open weights 975 HF downloads
  6. UniPASE Xiaobin Rong UniPASE is Xiaobin Rong and collaborators’ open audio-to-audio speech enhancement model for restori… Audio · Open weights 725 HF downloads
  7. Confucius4-TTS Youdao Confucius4-TTS is NetEase Youdao's open-source multilingual, cross-lingual zero-shot text-to-speech… Audio · Open weights 547 HF downloads
  8. Phonon 1 Fermion Research Phonon 1 is an open speech recognition model for English. It downloads in 415 MB and runs on a lapt… Audio · Closed 262 HF downloads
  9. Orpheus TTS Canopy Labs AI Orpheus TTS is Canopy Labs’ Llama-based 3B speech LLM for natural, emotionally controllable, multil… Audio · Open weights 166 HF downloads
  10. Eleven v3 ElevenLabs Eleven v3 is a text to speech model that generates expressive, emotionally rich speech controlled t… Audio · Closed 21 HF downloads
  11. Higgs Audio v3 TTS Boson AI Higgs Audio v3 TTS is Boson AI’s text-to-speech model for expressive conversational voice agents ac… Audio · Open weights 12 HF downloads
  12. ACE Step v1.5 StepFun ACE-STEP v1.5 is an open source, super fast music foundation model that uses a hybrid language mode… Audio · Open weights Open weights
  13. Atlas 1 Willow Atlas 1 is the voice AI model behind Willow, built for fast, high-accuracy dictation and polished s… Audio · Closed Closed weights
  14. Bland Speech v3 Bland Bland Speech v3 is a text to speech model trained on real human conversations rather than professio… Audio · Open weights Open weights
  15. Bulbul Sarvam AI Bulbul is a code mixed, multilingual text to speech model built for Indian languages. It offers six… Audio · Closed Closed weights
  16. Bulbul V4 Sarvam AI Bulbul V4 is Sarvam AI's latest text to speech model, building on Bulbul V3 with fine grained expre… Audio · Open weights Open weights
  17. Cabina transcriber v1 Cabina Cabina transcriber v1 is a real-time speech-to-text model with stable timestamps, punctuation, and… Audio · Open weights Open weights
  18. Chatterbox Turbo Resemble AI Chatterbox Turbo is the most efficient Chatterbox TTS variant, a compact MIT-licensed model that de… Audio · Closed text to speech pipeline
  19. Chirp 3 Google Chirp 3 is Google's latest multilingual automatic speech recognition (ASR) transcription model, off… Audio · Open weights Open weights
  20. CLOVA Voice Naver CLOVA Voice is NAVER’s neural text-to-speech service for lifelike, multilingual voices. It offers n… Audio · Closed Closed weights
  21. CLOVA Voice EMR Naver CLOVA Voice EMR is NAVER’s clinical speech solution for hospitals and clinics. It transcribes docto… Audio · Closed Closed weights
  22. Deepgram Flux TTS Deepgram Flux TTS is a conversation aware text to speech model built for real time voice agents. It reads fu… Audio · Open weights Open weights
  23. Dia 2 Nari Labs Dia2 is an open source streaming dialogue TTS model that generates speech in real time from partial… Audio · Open weights Open weights
  24. Dolphin Gemma Google DeepMind DolphinGemma is Google’s audio model for learning patterns in dolphin vocalizations and generating… Audio · Closed Closed weights
  25. Doubao Realtime Voice ByteDance Doubao Realtime Voice is ByteDance’s low-latency voice interface for the Doubao models—streaming sp… Audio · Closed Closed weights
  26. Eleven Flash v2.5 ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
  27. Eleven Multilingual ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
  28. Eleven v3 alpha ElevenLabs Eleven v3 (alpha) is ElevenLabs’ next-gen speech model for lifelike TTS, dubbing, and speech-to-spe… Audio · Closed Closed weights
  29. ElevenLabs Scribe ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
  30. FireRedASR2S FireRedTeam FireRedASR2S is an industrial-grade all-in-one ASR system combining ASR, VAD, LID, and punctuation… Audio FireRedTeam
  31. FireRedTTS 2 FireRedTeam FireRedTTS-2 is a long-form streaming TTS system for multi-speaker dialogue generation. Audio · Open weights Open weights
  32. Fish Speech Fish Audio Fish-Speech is an open multilingual text-to-speech system that uses large language models for lingu… Audio · Closed Closed weights
  33. Gemini 3.5 Live Translate Google DeepMind Gemini Audio is Google DeepMind’s closed-source native audio model family for low-latency live dial… Audio · Closed Closed weights
  34. Gemini 3.5 Transcribe Google DeepMind Gemini 3.5 Transcribe is a speech to text model offering low latency, high accuracy transcription w… Audio · Closed Closed weights
  35. Google Audio Neural2 Google Google Audio Neutral 2 is a clear, neutral TTS profile for information-dense content and profession… Audio · Closed Closed weights
  36. Google Audio Polyglot Google Google Audio Polyglot is a multilingual TTS style that handles code-switching and multiple accents. Audio · Closed Closed weights