Introduction

AmiVoice API is a speech recognition API that converts audio into text. When you send audio to AmiVoice API, it returns the spoken content as text. This allows you to create speech-enabled applications such as meeting transcription or voice dialogue systems.

Quick Start

1

Get your APPKEY

Register as a user and find your APPKEY in the [Connection Info] section on the My Page dashboard. Set it as an environment variable with the following command.

export AMIVOICE_APPKEY=your_appkey_here

2

Prepare an audio file

Prepare an audio file to transcribe. You can use the sample audio (test.wav) below right away.

For supported audio file formats, see Audio Formats.

3

Run speech recognition

Run the following. Replace test.wav with the path to your audio file.

curl

curl https://acp-api.amivoice.com/v1/recognize \
     -F d=-a-general \
     -F u=$AMIVOICE_APPKEY \
     -F a=@test.wav | jq

Python

import os
import requests

with open("test.wav", "rb") as f:
    response = requests.post(
        "https://acp-api.amivoice.com/v1/recognize",
        data={"d": "-a-general", "u": os.environ["AMIVOICE_APPKEY"]},
        files={"a": f}
    )
    data = response.json()
    print(data["text"])  # The JSON parser automatically converts Unicode escapes to readable text

4

Check the result

On success, you will receive JSON like the following. The text field contains the transcribed text.

{
  "results": [
    {
      "tokens": [ ... ],
      "confidence": 0.998,
      "starttime": 250,
      "endtime": 8794,
      "text": "アドバンスト・メディアは、人と機械との自然なコミュニケーションを実現し、豊かな未来を創造していくことを目指します。"
    }
  ],
  "utteranceid": "20220602/14/018122d637320a301bc194c9_20220602_141433",
  "text": "アドバンスト・メディアは、人と機械との自然なコミュニケーションを実現し、豊かな未来を創造していくことを目指します。",
  "code": "",
  "message": ""
}

For details about the response, see Speech Recognition Results.

Next Steps

For detailed API usage, refer to the following guides.

🔗 Developer Guide

Detailed information for API development, including interface selection, request parameters, and result formats.

🔗 Introduction & Operations Guide

Essential information for deploying and operating AmiVoice API in production environments.

Advanced Features

📄️ Engine Selection

Choose an engine optimized for your domain — medical, and more.

🔗 Streaming

Use the WebSocket interface to transcribe real-time audio sources like a microphone.

🔗 Batch Processing

For large files or high-volume audio, use the asynchronous HTTP interface for batch processing.

📄️ Word Registration

Register domain-specific terms and proper nouns to improve recognition accuracy.

🔗 Speaker Diarization

Separate audio containing multiple speakers and identify who spoke when.

🔗 Utterance Volume Tag

Use utterance volume tags to obtain aggregated information about speech segments.