Docs — Prosody

Quickstart

Try the playground with its limited trial. For API calls, request a key and send it in the X-API-Key header.

curl -X POST "https://api.prosody.studio/v1/scores" \
  -H "X-API-Key: $PROSODY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_data": "<base64 WAV audio>",
    "sample_rate": 16000,
    "language": "en-US",
    "reference_text": "The quick brown fox"
  }'

POST /v1/scores

Score one recording against its reference text. These four JSON fields are required.

Field	Value
`audio_data`	Base64-encoded WAV audio. Start with mono PCM at 16 kHz.
`sample_rate`	The WAV file's sample rate in Hz.
`language`	Use `en-US` for English.
`reference_text`	The words the speaker is expected to say.

Add the optional session_id query parameter to group recordings into a practice session.

Response

Standard responses include scores, word results, and phoneme detail. This example is an excerpt.

{
  "scores": {
    "pronunciation": 72.4,
    "script_adherence": 100.0,
    "overall": 72.4
  },
  "words": [
    {
      "word": "the",
      "status": "match",
      "acoustic_match": 68.1,
      "timing": {
        "start": 0.12,
        "end": 0.24,
        "duration_ms": 120
      },
      "phonemes": [
        { "detected": "DH", "acoustic_match": 71.2 }
      ]
    }
  ]
}

Use detail=summary for fewer fields or detail=full for additional mismatch diagnostics.

More endpoints

Batch scoring and stored results support practice workflows.

Endpoint	Purpose
`POST /v1/scores/batch`	Score multiple recordings in one request.
`GET /v1/scores/{result_id}`	Retrieve a stored result when its storage UUID is known.
Preview APIs Contracts may change.
`GET /v1/results` `GET /v1/history`	List stored scores and chronological practice history.
`GET /v1/sessions` `POST /v1/sessions`	List session summaries or create a practice session.
`GET /v1/sessions/{session_id}` `PATCH /v1/sessions/{session_id}`	Read, close, or abandon a session. Closed or abandoned sessions reject new scores.
`GET /v1/profile` `PUT /v1/profile`	Read preferences and learning stats; update profile preferences.

TypeScript SDK

Use @prosody/sdk for typed requests and response validation.

npm install @prosody/sdk

For Postman, import the collection and production environment.

Privacy

Audio is processed for scoring and is not retained by the playground.
Authenticated score metadata may be stored for result and history views.
Audio is not sent to third-party speech APIs.
Training use requires explicit consent, separate from the trial flow.

Request an API key

Email francois@prosody.studio with a short description of what you are building and your expected audio volume.