vidu-audio-clone

Clone a real human voice and use it to read the specified text.

Overview

Field	Value
Model ID	`vidu-audio-clone`
CLI	`dlazy vidu-audio-clone`
MCP	`vidu-audio-clone` (Claude Code surfaces this as `mcp__dlazy__vidu-audio-clone`)
Type	`audio`
Execution	Async task; the CLI polls until completion (`--no-wait` returns `generateId` immediately)
Batch	Supports `--batch <n>` parallel fan-out

Parameters

Arg	Type	Required	Notes
`audio_url`	url	Yes	Audio URL; audio (accepts URL, local path, or data: URL)
`prompt`	string	Yes	Prompt

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy vidu-audio-clone --help
dlazy vidu-audio-clone --audio_url "https://example.com/source.mp3" --prompt "Write your prompt here"
dlazy vidu-audio-clone --audio_url "./local-audio.mp3" --prompt "Write your prompt here"
dlazy vidu-audio-clone --audio_url "https://example.com/source.mp3" --prompt "Write your prompt here" --dry-run
dlazy vidu-audio-clone --audio_url "https://example.com/source.mp3" --prompt "Write your prompt here" --no-wait
dlazy vidu-audio-clone --audio_url "https://example.com/source.mp3" --prompt "Write your prompt here" --batch 4

Compose with a pipeline

dlazy gemini-2.5-tts --prompt "reference voice line" \
  | dlazy vidu-audio-clone --audio_url - --prompt "Write your prompt here"

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__vidu-audio-clone; generic clients (e.g. OpenClaw) call it as vidu-audio-clone.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "audio", "id": "o_...", "url": "https://files.dlazy.com/result.mp3", "mimeType": "audio/mpeg" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.