PAA: English Pronunciation Assessment Agent

Developers: A2A usage

• Agent Card URL: /.well-known/agent.json
• A2A JSON-RPC endpoint: /a2a (methods: agent.about, pronunciation.evaluate)
• Health endpoint: /healthz
• request_id: -

Example request: pronunciation.evaluate

This service provides an A2A-compatible JSON-RPC endpoint for remote agents to evaluate freeform spoken English across four constructs (Pronunciation, Stress, Fluency, Grammar).

{
  "jsonrpc": "2.0",
  "id": "1",
  "method": "pronunciation.evaluate",
  "params": {
    "audio_wav_base64": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAEAfAAABAAgAZGF0YQAAAAA=",
    "native_exemplar": false,
    "deepgram_api_key": "optional_override_key"
  }
}

Example response

This sample shows the structure you receive after a successful pronunciation.evaluate call. The analysis block contains the transcript and the 4 metrics. Use this shape to map results into UI components and interpret success.

{
  "jsonrpc": "2.0",
  "id": "1",
  "result": {
    "analysis": {
      "scores": {
        "fluency": 3.75,
        "language_use": 0.95,
        "pronunciation": 0.89,
        "stress": 1.0
      },
      "targets": [],
      "timing": {
        "bucket_json_read_process_sec": 0.001,
        "deepgram_api_sec": 0.45,
        "gemini_api_sec": 1.2,
        "persist_output_files_sec": 0.0,
        "pocketsphinx_alignment_sec": 0.0,
        "recording_duration_sec": 5.0
      },
      "transcript": "hello world"
    },
    "persistence": {
      "json_path": "/bucket/abcd.json",
      "recording_id": "abcd",
      "wav_path": "/bucket/abcd.wav"
    },
    "request_id": "req-1234"
  }
}