See the sound, hear the visual. Generate complete audio-visual videos in a single pass — with natural voiceovers, matching sound effects, and ambient atmosphere. No more tedious editing.
The first "Native Audio" model that transforms AI video creation from silent visuals to immersive audio-visual experiences.
First model to generate visuals, voiceovers, sound effects, and ambient atmosphere in a single pass. Seamless integration of camera rhythm and emotional tone transforms content from "viewable" to "immersive."
Voice rhythm, ambient sounds, and visual actions are closely aligned. Eliminates the disconnect between "visuals and separate audio" with seamless coordination in rhythm, emotion, and narrative expression.
Choose who speaks, what they say, and the emotion behind it. Generate ambient and special effects sounds freely, adjusting the pace and atmosphere to fit various creative needs with complete control.
No complex operations required — just input text or images, and the system automatically handles sound and visual details. Ideal for content creators and small studios to quickly produce professional videos.
Kling VIDEO 2.6 Pro is Kling's first "Native Audio" video generation model, developed by Kuaishou Technology. This groundbreaking model simultaneously produces video visuals and complete audio — including voiceovers, sound effects, and ambient sounds — in a single generation. This innovation completely transforms the traditional AI video workflow from "first generating silent visuals, then manually adding voiceovers and sound effects" to generating complete audio-visual content in one pass.
Previously, Kling's video models could only generate "silent visuals," requiring creators to manually find voiceovers, add sound effects, and adjust the pace — an overly complex process that made it hard to achieve true immersion. Now, with VIDEO 2.6 Pro, creators can instantly create dynamic videos that are complete with sound, rhythm, and immersion — no more tedious editing.
The model focuses on three core upgrades: Audio-Visual Coordination ensures voice rhythm, ambient sounds, and visual actions are closely aligned; Audio Quality delivers cleaner sound with richer layers that closely mimic real mixing effects; and Semantic Understanding provides strong comprehension of text descriptions, spoken language, and complex storylines, ensuring more accurate interpretation of creator intentions.
From a sentence to a complete audio-visual video. Input text to generate videos with voiceovers, sound effects, and ambient sounds. The system automatically handles all sound and visual details.
Bring static images to life with sound and motion. Upload images with text prompts to instantly create audio-visual content. Perfect for expanding existing images into full audio-visual experiences.
Characters speak directly to the camera with natural emotion and synchronized lip movements. Perfect for product showcases, lifestyle vlogs, news broadcasts, and public speaking.
Natural conversations between multiple characters with accurate dialogue flow and emotional expression. Ideal for storytelling, dramatic scenes, and interactive content.
Characters singing or rapping with lyrics and musical backgrounds. Create music videos, creative content, and artistic performances with synchronized vocals and instrumentals.
Rich environmental sounds and action effects. Wind, ocean waves, footsteps, glass breaking, and more. Create immersive experiences with mixed sound effects that closely mimic real mixing.
| Duration | 5s, 10s |
|---|---|
| Aspect Ratio | 16:9, 1:1, 9:16 |
| Batch Output | Up to 4 videos |
| Quality | 1080p HD |
| Languages | Chinese, English |
|---|---|
| Audio Types | 6 Types |
| Synchronization | Perfect Sync |
| Quality | Studio Grade |
| Text-to-AV | Supported |
|---|---|
| Image-to-AV | Supported |
| Audio Toggle | Optional |
| Platforms | Web, App |
| Voice Narration | Character voice with natural emotion and lip-sync — Vlogs, Product Demos, Tutorials |
|---|---|
| Dialogue | Multi-person conversations with natural flow — Stories, Drama, Interviews |
| Singing/Rap | Musical performances with lyrics — Music Videos, Creative Content |
| Ambient Sounds | Environmental background sounds — Nature Scenes, Urban Settings |
| Action Effects | Object and action sound effects — Action Scenes, Product Demos |
| Mixed Effects | Combination of voice, ambient, and effects — Immersive Experiences, Films |
Display products and highlight key selling points with clear speech, natural tone, and matching atmosphere. Perfect for e-commerce, live-streaming, and product demonstrations with synchronized audio-visual content.
Showcase easy, natural moments from daily life with authentic voiceovers and ambient sounds. Create immersive vlogs with synchronized audio that captures the atmosphere and emotion of every moment.
Emphasize professionalism, formality, and stable tone with clear speech and background sounds. Ideal for news broadcasts, interviews, and journalistic content with studio-quality audio-visual production.
Show strong, persuasive delivery with passionate voice and emotional expression. Perfect for speeches, presentations, and motivational content with synchronized audio that captures the speaker's energy and conviction.
Create music videos with characters singing or rapping with lyrics and musical backgrounds. Perfect for creative content, artistic performances, and musical storytelling with synchronized vocals and instrumentals.
Combine various sound effects and environmental sounds to create unique audio-visual experiences. Ideal for creative projects, artistic works, and experimental content with immersive mixed audio effects.
The model currently supports Chinese and English voice output. If you input other languages, the model will automatically translate them to English for voice generation without affecting the overall video output. For optimal results, use Chinese or English prompts.
Current generation supports 5 and 10 second durations. For singing or dialogue scenes, using the 10s parameter is recommended for more complete and stable results. Longer videos require generating multiple segments.
In the Image-to-Video feature, the video quality is highly dependent on the input image resolution. For better video quality, it's recommended to upload higher-resolution images. Low-resolution inputs may result in lower quality outputs.
While the model generates high-quality audio, certain specific sound effects or tones may require multiple iterations to achieve the ideal result. Detailed prompts with clear emotional and tonal descriptions help improve first-generation quality.
Experience the first native audio video generation model. See the sound, hear the visual. Create complete audio-visual videos in a single pass.
Try Kling 2.6 Pro now