PulseAugur
EN
LIVE 09:20:22

Kandinsky S2V 1.0: Open-source audio-driven avatar video generation models released

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced Kandinsky S2V 1.0, a new family of open-source models designed for generating human avatar videos driven by audio. The models, available in Lite (2B parameters) and Pro (21B parameters) versions, can produce long-form videos with synchronized lip movements, expressions, and gestures from a single reference image, speech waveform, and text prompt. Evaluations show that Kandinsky S2V 1.0 Pro performs comparably to or better than leading open-source and proprietary models, particularly in lip synchronization. The project also includes distilled variants for faster generation and releases code, checkpoints, and integrations under the MIT license to foster open research. AI

IMPACT Accelerates open research in audio-driven avatar video generation with the release of performant, open-source models.

RANK_REASON The item describes a new research paper detailing a novel model family for audio-driven video generation, including performance benchmarks and code release. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Kandinsky S2V 1.0: Open-source audio-driven avatar video generation models released

How we ranked this

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new research paper detailing a novel model family for audio-driven video generation, including performance benchmarks and code release. [lever_c_demoted from research: ic=1 ai=…
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 Svenska(SV) · Nikolay Semenov, Artem Riabinin, Sergey Bassenko, Anna Averchenkova, Julia Agafonova, Anastasia Aliaskina, Kirill Kozlov, Lev Novitskiy, Nikita Samsonov, Nikolai Gerasimenko, Denis Dimitrov ·

    Kandinsky S2V 1.0: Audio-Driven Avatar Video Generation

    arXiv:2610.19290v1 Announce Type: new Abstract: We present Kandinsky S2V 1.0, an open family of speech-to-video models for controllable audio-driven human animation, comprising Kandinsky S2V 1.0 Lite (2B parameters) and Kandinsky S2V 1.0 Pro (21B parameters). From a single refere…

RELATED ENTITIES

RELATED TOPICS