Audio

Kokoro Text to Speech

Type English text and download natural speech as a 24 kHz WAV. Free text to speech on devices you connect.

Kokoro by hexgrad; ONNX conversion by ONNX Community

Model licenses

kokoro-tts pinned ONNX checkpoint and associated assets · Apache-2.0

Retain licence, copyright and publisher attribution notices; no trademark endorsement. Publisher model-card cautions are preserved in the distributed notice.

Distributed license

Notice

FreeOnlineUnlimitedKokoro by hexgrad; ONNX conversion by ONNX Community API access

API reference

Submit via REST

Use your personal API key (msk_…) to create jobs for this workload from your own tools. Jobs started this way run on the same devices you connected on Your Devices — at least one has to be online.

Hide API details
POSThttps://cp.meshlabs.cloud/v1/organizations/jobs

Authenticate with X-Organization-Api-Key: msk_your_personal_api_key. The header name matches org keys; personal keys use the same endpoint.

Request body

{
  "workload_type": "kokoro-tts",
  "job_spec": {
    "prompt": "A photorealistic lighthouse at dusk",
    "voice": "af_heart",
    "speed": 1
  }
}

job_spec fields

FieldRequiredDefaultDescription
promptYes—Text to speak. English; American or British from the voice prefix.
voiceNoaf_heartaf_heart is the community default. af_/am_ American, bf_/bm_ British. Style vector from the published pack.
speedNo1Speech-rate multiplier. 1.0 is natural (community default); lower is slower.
phonemesNo—Optional Kokoro IPA. When set, G2P is skipped.

cURL

curl -X POST https://cp.meshlabs.cloud/v1/organizations/jobs \
  -H "X-Organization-Api-Key: msk_your_personal_api_key" \
  -H "Content-Type: application/json" \
  -d '{
  "workload_type": "kokoro-tts",
  "job_spec": {
    "prompt": "A photorealistic lighthouse at dusk",
    "voice": "af_heart",
    "speed": 1
  }
}'
GEThttps://cp.meshlabs.cloud/v1/organizations/jobs/{job_id}

Poll with the same API key until status is terminal (COMPLETED, FAILED, CANCELED, or MODERATION_BLOCKED). When content moderation is enabled, jobs may start in MODERATION_PENDING before entering the compute queue. Completed jobs include presigned download_url values on each output.

Create response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "kokoro-tts",
  "status": "PENDING",
  "job_spec_json": {
    "prompt": "A photorealistic lighthouse at dusk",
    "voice": "af_heart",
    "speed": 1
  },
  "work_units": [],
  "outputs": [],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "2026-06-08T12:00:00Z"
}

Completed response

{
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "workload_type": "kokoro-tts",
  "status": "COMPLETED",
  "job_spec_json": {
    "prompt": "A photorealistic lighthouse at dusk",
    "voice": "af_heart",
    "speed": 1
  },
  "work_units": [
    {
      "id": "…",
      "index": 0,
      "status": "COMPLETED"
    }
  ],
  "outputs": [
    {
      "id": "…",
      "output_type": "<output type>",
      "filename": "<output filename>",
      "size_bytes": 524288,
      "download_url": "<presigned output download URL>"
    }
  ],
  "created_at": "2026-06-08T12:00:00Z",
  "updated_at": "<completion timestamp>"
}

Type English text, pick a Kokoro voice, and download spoken audio as a 24 kHz WAV — free, unlimited text-to-speech on devices you connect. Voices are English and British. The model is Apache-2.0, so you can use the audio under that licence, including commercially. The first run downloads the model onto your devices; later runs are faster. This speaks text in a built-in voice. To clone a voice from your own recording, use Chatterbox.