Superseded by Kling 3.0, though creators wanting short clips with sound in one pass can still use it on credits.
Kenning's take
What it does
Kling VIDEO 2.6 makes video and matching audio in one pass, including voiceover, dialogue, singing, sound effects and background atmosphere. Voices are in Chinese and English, and clips run 5 or 10 seconds. It is available in the Kling AI app and site, where it costs credits per second, and it has since been followed by Kling 3.0.
- Native audio generated with the video
- Voiceover, dialogue, singing and sound effects
- Chinese and English voices
- 5 or 10 second clips
- Voice Control add-on
Who it suits. Creators who want short AI video clips with sound without adding audio separately.
Key facts
- Category
- AI models
- Part of
- Kling AI
- Made by
- Kuaishou (Kling AI)
- Based in
- China
- Launched
- 2025
- How to get it
- in the Kling AI web app and mobile apps, paid in credits; free Basic accounts get no monthly credits
- Works on
- Web, iOS, Android
- Free plan
- Basic plan at $0 with no monthly credits
Pricing
| Plan | Price | Billed |
|---|---|---|
| Basic | $0 | month |
| Standard (first-subscription offer; renews at $8.80) | $6.99 | month |
| Pro (first-subscription offer; renews at $32.56) | $25.99 | month |
| Premier (first-subscription offer; renews at $80.96) | $64.99 | month |
| Ultra (first-subscription offer; renews at $159.99) | $127.99 | month |
FAQ
What is new in Kling 2.6?
It generates speech, sound effects and ambient sound together with the video, in Chinese or English.
How much does Kling 2.6 cost?
It uses Kling credits: 10 credits per second with native audio in Professional mode, or 5 per second without audio.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Kling 3.0
Kling's video model with clips up to 15 seconds, multi-shot scenes and audio in five languages
Kling O1
Kling video model that handles generation and text-prompted editing of video in one system
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.