Audio & Voice — Explore AI Tools & Stories

Fresh stories

New

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

A Freepik Spaces workflow now uses Nano Banana 2 for stills, Veed Fabric for closeup lipsync, OmniHuman for directed performance, and Kling 3.0 for motion clips. Split one music video into model-specific stages instead of forcing a single tool to handle everything.

Workflow🎵Freepik1d ago

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

Workflow🎵Freepik1d ago

Top storiesthis week

See all →

Breaking

KittenTTS releases v0.8 with a 25MB int8 model and CPU-only speech synthesis

KittenML's latest open-source TTS release spans 15M to 80M models, with the smallest coming in under 25MB and the larger one reportedly running faster than realtime on CPU. Audio creators should test pronunciation and install overhead before betting on it for edge or local voice tools.

New

Voice·2d ago·2 min read

New

Fun-CineForge opens multi-speaker dubbing with temporal modality and a dataset pipeline

Tongyi Lab opened Fun-CineForge with multi-speaker dubbing, temporal modality for off-screen or blocked faces, and a full dataset-building pipeline. It matters for dialogue and localization workflows that break on hard cuts, overlapping speech, or missing lip cues.

Release🎵Lip Sync1w ago

See all stories →

New

KittenTTS releases v0.8 with a 25MB int8 model and CPU-only speech synthesis

Release🎵VoiceLocal Inference2d ago · 2 min read

Fun-CineForge opens multi-speaker dubbing with temporal modality and a dataset pipeline

Release🎵Lip Sync1w ago

Workflows you can try today

Step-by-step guides →

Today's Pick

⚡

Freepik

1d ago

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

FreepikKlingNano Banana

Runway launches Characters API: real-time avatars with custom voices and knowledge banks

Release🎵Runway2w ago

Explore what's new in AI

Filter by tag in Audio & Voice

Fresh stories

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

Top storiesthis week

KittenTTS releases v0.8 with a 25MB int8 model and CPU-only speech synthesis

Fun-CineForge opens multi-speaker dubbing with temporal modality and a dataset pipeline

KittenTTS releases v0.8 with a 25MB int8 model and CPU-only speech synthesis

Fun-CineForge opens multi-speaker dubbing with temporal modality and a dataset pipeline

Workflows you can try today

Freepik

Freepik Spaces supports music-video lipsync with Veed Fabric 1.0 Fast and OmniHuman 1.5

Grok launches Text-to-Speech API with expressive controls and LiveKit support

ElevenLabs launches Flows in ElevenCreative with 35-plus image and video models

Freepik launches Speak: lip-synced videos in 30+ languages, up to 5 minutes

Runway launches Characters API: real-time avatars with custom voices and knowledge banks