audio AI Models

🤖 Model 📝 → 🔊

camenduru/metavoice

Convert text to speech using MetaVoice-1B, a 1.2 billion parameter audio model trained on 100,000 hours of speech. Input...

📝 → 🔊 • text-to-speech • audio-synthesis • speech-generation • 12.5K runs

🤖 Model 🖼️ → 🎥

camenduru/one-shot-talking-face

Generate a talking face video from a single image and an audio file. This model creates a video output where the face in...

🖼️ → 🎥 • talking-face • lip-sync • image-to-video • 1.8K runs

🤖 Model 📝 → 🔊

lilcats/kitten-tts

Generate speech from text input using an ultra-lightweight, CPU-friendly text-to-speech model. Supports multiple built-i...

📝 → 🔊 • text-to-speech • tts • cpu-friendly • 7 runs

🤖 Model 🎥

corywilkerson/animal-to-train

Generate psychedelic videos from animal names, transforming them into trippy train visuals with optional psychedelic aud...

🎥 • video-generation • psychedelic • animal-transformation • 2 runs