AgentEarth
登录

Ae · Whisper

22.58积分/次
ae_whisper

将音频文件转写为文本，可选择翻译为英语、添加时间戳和识别说话人。

转录音频
22.58积分/次

价格说明

22.58积分/次

API 调用

通过统一工具网关发起同步请求，鉴权和计费由 AgentEarth 处理。

cURL
curl --request POST \
  --url 'https://api.agentearth.ai/v1/tools/run' \
  --header 'Authorization: Bearer $AGENTEARTH_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "tool": "ae_whisper",
  "input": {
    "task": "transcribe",
    "prompt": "xxx",
    "diarize": "false",
    "language": "xxx",
    "audio_url": "xxx",
    "batch_size": "64",
    "chunk_level": "segment",
    "num_speakers": "xxx"
  }
}'
请求方式
POST
接口地址
/v1/tools/run
鉴权方式
Bearer Token
超时时间
60 秒
当前版本
—
响应示例
{
  "error_no": 0,
  "error_msg": "",
  "result": [
    {
      "type": "text",
      "text": "xxx"
    }
  ],
  "platform_annotations": {
    "source": "AgentEarth",
    "platform_note": "xxx",
    "platform_suggestion": "xxx"
  }
}

工具参数

未传入的可选参数将使用平台默认值。

参数类型必填说明默认值
taskenum (transcribe | translate)否Task to perform on the audio file. Either transcribe or translate.transcribe
promptstring否Prompt to use for generation. Defaults to an empty string.—
diarizeboolean否Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time.false
languagestring否 Language of the audio file. If set to null, the language will be automatically detected. Defaults to null. If translate is selected as the task, the audio will be translated to English, regardless of the language selected. —
audio_urlstring是URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.—
batch_sizeinteger否暂无参数说明。64
chunk_levelenum (none | segment | word)否Level of the chunks to return. Either none, segment or word. `none` would imply that all of the audio will be transcribed without the timestamp tokens, we suggest to switch to `none` if you are not satisfied with the transcription quality, since it will usually improve the quality of the results. Switching to `none` will also provide minor speed ups in the transcription due to less amount of generated tokens. Notice that setting to none will produce **a single chunk with the whole transcription**.segment
num_speakersinteger否 Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected. —