generated: '2026-09-06'
method: searched
source: >-
  https://developers.daglo.ai/guide/en/STT-Async.html, https://developers.daglo.ai/guide/Quick-Speech-Voice-To-Text.html,
  https://developers.daglo.ai/guide/Language-chat-completion.html, https://developers.daglo.ai/guide/Language-Text-To-Speech.html,
  https://developers.daglo.ai/guide/Polling-and-Callback.html
note: >-
  Request/response examples exactly as ActionPower publishes them. Placeholder tokens are the provider's
  own (<API_TOKEN>); the sample audio URL and the expected transcript are real and callable.
  The production OpenAPI also carries 36 in-spec `example:` values on individual fields.
examples:
  - name: Submit long audio for asynchronous transcription
    operation: post-stt-v1-async-transcripts
    request:
      method: POST
      url: https://apis.daglo.ai/stt/v1/async/transcripts
      headers:
        Content-Type: application/json
        Authorization: 'Bearer <API_TOKEN>'
      body: |-
        {
            "audio": {
                "source": {
                    "url": "https://storage.googleapis.com/bkt-actionpower-examples/audio/actionpower_hello.wav"
                }
            }
        }
    response:
      status: 200
      body: '{"rid":"12345678-abcd-efgh-1234-abcdefghijkl"}'
  - name: Poll an asynchronous transcription
    operation: get-stt-v1-async-transctips-rid
    request:
      method: GET
      url: https://apis.daglo.ai/stt/v1/async/transcripts/<RID>
      headers:
        Authorization: 'Bearer <API_TOKEN>'
    response:
      status: 200
      body: |-
        {
            "rid": "12345678-abcd-efgh-1234-abcdefghijkl",
            "status": "transcribed",
            "sttResults": [
                {
                    "transcript": "안녕하세요. 액션 파워입니다.",
                    "words": [
                        {
                            "word": "안녕하세요. ",
                            "startTime": { "nanos": 60000000, "seconds": "0" },
                            "endTime":   { "nanos": 860000000, "seconds": "0" },
                            "segmentId": "1"
                        }
                    ],
                    "keywords": null
                }
            ]
        }
  - name: Register a callback instead of polling
    operation: post-stt-v1-async-transcripts
    request:
      method: POST
      url: https://apis.daglo.ai/stt/v1/async/transcripts
      body: |-
        {
            "callback": {
                "url": "https://client.example.com/callback",
                "headers": { "<Header1_KEY>": "<Header1_Value>" }
            }
        }
    callback_delivery:
      method: POST
      url: https://client.example.com/callback
      headers:
        Content-Type: application/json
      body: |-
        {
          "status": "transcribed",
          "sttResults": [ { "transcript": "안녕하세요, 예제입니다." } ]
        }
  - name: Generate a chat completion
    operation: post-nlp-v1-sync-chat-completions
    contract_note: >-
      Documented in the guide and present in openapi/actionpower-daglo-cloud-api-dev-openapi.yml only —
      the production document does not describe this endpoint.
    request:
      method: POST
      url: https://apis.daglo.ai/nlp/v1/sync/chat/completions
      headers:
        Content-Type: application/json
        Authorization: 'Bearer <API_TOKEN>'
      body: |-
        {
            "model": "elli",
            "messages": [
                { "role": "system", "content": "당신은 초등학교 교사입니다." },
                { "role": "user", "content": "금리에 대해서 초등학생이 이해 가능한 수준으로 설명해 주세요." }
            ],
            "topP": 0.9
        }
    response:
      status: 200
      body: |-
        {
            "rid": "<RID>",
            "model": "elli",
            "chatResults": [
                {
                    "index": 0,
                    "message": { "role": "assistant", "content": "..." },
                    "finishReason": "stop"
                }
            ],
            "usage": { "promptTokens": 23, "completionTokens": 78, "totalTokens": 101 }
        }
  - name: Synthesize speech
    operation: post-tts-v1-sync-audios
    request:
      method: POST
      url: https://apis.daglo.ai/tts/v1/sync/audios
      headers:
        Content-Type: application/json
        Authorization: 'Bearer <API_TOKEN>'
      body: '{ "text": "안녕하세요. 액션파워입니다."}'
    response:
      status: 200
      content_type: audio/wav
      body: a WAV file
    voices:
      - {id: en_US_Olivia, language: en_US, description: 'Olivia — adult, female, friendly'}
      - {id: ko_KR_Jimin, language: ko_KR, description: 'Jimin — adult, female, calm'}
  - name: Realtime streaming transcription (gRPC)
    contract: grpc/actionpower-speech.proto
    request:
      command: python client.py --server apis.daglo.ai --token $API_TOKEN
      metadata:
        authorization: 'Bearer <API_TOKEN>'
      audio: LINEAR16, 16000 Hz, mono, 0.25s chunks
      config: '{language_code: ko-KR, interim_results: true, max_silence_ms: 2500}'
    response:
      stream: StreamingRecognizeResponse with StreamingRecognitionResult {transcript, is_final, language_code}