{
  "formatVersion": 1,
  "scope": "Curated public research extract; not the full raw run.",
  "canonical": "https://embiro.ai/research/kokoro-french-voice",
  "fieldNote": 11,
  "slug": "kokoro-french-voice",
  "title": "Bonjour, Kokoro.",
  "description": "A small French voice feasibility test, followed by broader CPU comparisons.",
  "category": "Speech",
  "art": "speech-wave",
  "thumbnail": {
    "src": "/research/thumbnails/kokoro-french-voice.webp",
    "alt": "An ivory speech bubble floating above a forest-green speaker."
  },
  "date": "2026-10-12",
  "published": "2026-10-12",
  "updated": "2026-10-12",
  "author": "Embiro Labs Research",
  "status": "Exploratory benchmark",
  "headline": "French speech without a GPU requirement.",
  "metric": "3",
  "metricLabel": "French prompts tested",
  "method": [
    "Kokoro on CPU using the ff_siwis French voice. Three synthetic service messages; one generation per prompt. Model load was measured separately at 1.36 seconds."
  ],
  "sections": [
    {
      "title": "What ran",
      "paragraphs": [
        "All three prompts generated valid audio: a welcome, payment acknowledgement and team introduction. Generation ranged from 1.98 to 3.41 seconds for 3.98–6.38 seconds of audio."
      ]
    },
    {
      "title": "Scope of the decision",
      "paragraphs": [
        "Kokoro became the French TTS pilot option. This initial smoke test does not establish African French accent quality. The later Azure CPU study repeats matched French prompts and provides a stronger hardware comparison with listening samples."
      ]
    }
  ],
  "limitations": [
    "Three synthetic prompts, no blind listening assessment and no accent-specific validation. A successful audio file is not proof of complete or natural pronunciation."
  ],
  "tables": [
    {
      "title": "French feasibility",
      "columns": [
        "Prompt",
        "Generation (s)",
        "Audio (s)"
      ],
      "rows": [
        [
          "Welcome",
          "2.35",
          "4.62"
        ],
        [
          "Payment",
          "1.98",
          "3.98"
        ],
        [
          "Introduction",
          "3.41",
          "6.38"
        ]
      ],
      "note": "One sample per prompt; load time is excluded."
    }
  ],
  "references": [
    {
      "label": "Kokoro · model card",
      "url": "https://huggingface.co/hexgrad/Kokoro-82M"
    }
  ],
  "audio": [],
  "evidence": [
    {
      "file": "results.json",
      "sha256": "72c1402af75adc57370aeb3d40fccedbfb6daed7c38e621a01a42b041df60a71"
    }
  ]
}