Models

72 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

Most downloaded A–Z Recently synced

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
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
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
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
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
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
Chatterbox Multilingual Resemble AI AI model by Resemble AI Audio · Closed 2.3k HF downloads
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
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
Eleven v3 ElevenLabs Eleven v3 is a text to speech model that generates expressive, emotionally rich speech controlled t… Audio · Closed 21 HF downloads
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
Bulbul Sarvam AI Bulbul is a code mixed, multilingual text to speech model built for Indian languages. It offers six… Audio · Closed Closed weights
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
CLOVA Voice Naver CLOVA Voice is NAVER’s neural text-to-speech service for lifelike, multilingual voices. It offers n… Audio · Closed Closed weights
CLOVA Voice EMR Naver CLOVA Voice EMR is NAVER’s clinical speech solution for hospitals and clinics. It transcribes docto… Audio · Closed Closed weights
Dolphin Gemma Google DeepMind DolphinGemma is Google’s audio model for learning patterns in dolphin vocalizations and generating… Audio · Closed Closed weights
Doubao Realtime Voice ByteDance Doubao Realtime Voice is ByteDance’s low-latency voice interface for the Doubao models—streaming sp… Audio · Closed Closed weights
Eleven Flash v2.5 ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
Eleven Multilingual ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
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
ElevenLabs Scribe ElevenLabs AI model by ElevenLabs Audio · Closed Closed weights
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
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
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
Google Audio Neural2 Google Google Audio Neutral 2 is a clear, neutral TTS profile for information-dense content and profession… Audio · Closed Closed weights
Google Audio Polyglot Google Google Audio Polyglot is a multilingual TTS style that handles code-switching and multiple accents. Audio · Closed Closed weights
Google Audio WaveNet Google Google Audio WaveNet is a natural-sounding TTS voice based on WaveNet-style synthesis, focused on l… Audio · Closed Closed weights
GPT Live 1 OpenAI GPT Live 1 is OpenAI's full duplex voice model for the API, built for real time voice agents that l… Audio · Closed Closed weights
GPT Live 1 OpenAI GPT-Live-1 is a full-duplex voice model that listens and speaks simultaneously for natural, real-ti… Audio · Closed Closed weights
GPT Live 1 mini OpenAI GPT-Live-1 mini is a smaller full-duplex voice model that listens and speaks simultaneously for nat… Audio · Closed Closed weights
GPT Live Transcribe OpenAI Low latency streaming speech to text model built for live audio, such as a microphone or call, wher… Audio · Closed Closed weights
GPT Transcribe OpenAI Speech to text model for completed audio files, streamed file transcripts, and committed turns in R… Audio · Closed Closed weights
Grok Voice Think Fast 2.0 xAI Grok Voice Think Fast 2.0 is a speech-to-speech voice model built for real-time conversational voic… Audio · Closed Closed weights
Hailuo Audio 01 music MiniMax Hailuo Audio 01 music is an earlier music generation model for hooks, riffs, and ambient beds. Audio · Closed Closed weights
Hailuo Audio 2.0 music MiniMax Hailuo Audio 2.0 music generates short musical clips from text and style prompts. Audio · Closed Closed weights
Hailuo Audio 2.5 hd MiniMax Hailuo Audio 2.5 hd is a high-fidelity TTS model for production-quality narration and content. Audio · Closed Closed weights