Evidence · first-party tested

The clean-input output was rated about 70–80% human-like and sounded smooth and pleasant, but some words lacked natural delivery in longer passages.

The observation

Criterion: Naturalness · Scenario: High-Quality Voice Sample (group: voice-cloning-inputs)

Query this

get_evidence({
  tool: "vocalai",
  scenario: "voice-cloning-inputs"
})

MCP · mcp.aidemos.com/api/mcp
Free with attribution.

Same input, other tools

Real outputs, no retouching · every cell queryable via API & MCP · aidemos.com