Voice changer

Takes a recording and says the same thing, with the same timing and delivery, in another voice.

Step by step

1. Add a Generate audio node and set Operation to Voice changer.
2. Wire an audio node or a video node into it. A video contributes its soundtrack. If several are wired, the first audio is used, otherwise the first video.
3. Pick a Model: eleven_multilingual_sts_v2 (default) or eleven_english_sts_v2.
4. Pick a Voice and, if you like, the Stability, Similarity and Style sliders, as in Text to speech.
5. Press Generate.

Ports

Input: audio or video. Output: audio.

Cost

$0.12 per minute of result, about 14 credits a minute. See Audio.

Agents and MCP

run_node_generation with medium: "audio" and params: { "operation": "voice_changer", "voiceId": "<id>" }, on a node that has the media wired in.