videospeech
Kling Video V2.6
Kling 2.6 Pro image- and text-to-video with integrated speech synthesis and 5 and 10-second control.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 4
- Eligible
- 4
- Input schemas imported
- 4 / 4
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Kling 2.6 Pro integrates speech synthesis into generation, pairing cinematic motion with native Chinese and English voice output. Dialogue embeds directly in prompts for automatic voicing matched to lips and scene timing. Duration runs 5 or 10 seconds; single images animate with scene continuity. Motion-control endpoints join the pro and standard tiers.
Capabilities
- Integrated Chinese and English speech synthesis
- Prompt-embedded dialogue voicing
- 5 and 10-second duration control
- Lip-matched AV coherence
Best for
- Social media creation
- Marketing production
- Cinematic prototyping
Use cases
- Speaking-character clips
- No-stitch AV content
- Coherent short narratives
Endpoints
4 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/kling-video/v2.6/pro/image-to-video | image to video | Eligible | 7 fields · requires prompt, start_image_url |
fal-ai/kling-video/v2.6/pro/motion-control | video editing | Eligible | 5 fields · requires image_url, video_url, character_orientation |
fal-ai/kling-video/v2.6/pro/text-to-video | text to video | Eligible | 6 fields · requires prompt |
fal-ai/kling-video/v2.6/standard/motion-control | video editing | Eligible | 5 fields · requires image_url, video_url, character_orientation |
Questions
Separate audio workflow?
No: speech synthesizes inside the pipeline.
Which voices?
Chinese and English output.