Kling 4.0 nails the lips but its audio comes out muffled (about 12 dB less above 12 kHz than a real mic). This board keeps Kling's take and timing and swaps only the voice with speech to speech, into a clone of your real voice, so the lips still match. Add your face refs, a start frame and 30 s of your voice, write your line in the prompt, run.
Fork to your canvas makes a full copy in your account, every node and edge on a fresh canvas. Add to an existing workflow drops it into one of yours as a single collapsed node: its inputs become ports on the left and its outputs ports on the right, so you wire it like any other node.
Inputs and what's baked in
Overridable inputs become sockets on the left of the node. Baked ones are served as outputs, so you get the author's asset without supplying your own.
- Overridable input1 · TAKE PROMPT · your line goes in the quotesinput:text · TEXT
- Overridable inputREF · your face, front (identity only)input:image · IMAGE
- Overridable inputREF · your face, 3/4 (identity only)input:image · IMAGE
- Overridable inputSTART FRAME · a still of you, lips closed, in your settinginput:image · IMAGE
- Overridable inputVOICE SAMPLE · about 30 s of your real voice, one speaker, no musicinput:image · IMAGE
Ask Claude for your next ad.
Connect once. Ask any time.
- No credit card
- You keep the rights to what you make
- Cancel anytime

