POST
/
audio
/
transcriptions
语音识别接口
curl --request POST \
  --url https://geekai.co/api/v2/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "doubao-transcribe",
  "audio": {
    "url": "https://example.com/audio.wav",
    "format": "mp3"
  },
  "retries": 0
}'
{
  "text": "<string>",
  "duration": 123
}

Authorizations

Authorization
string
header
required

JWT认证token

Body

application/json
model
string
default:doubao-transcribe
required

语音识别模型

audio
object
required

音频文件信息

retries
integer
default:0

自动重试次数,默认0,表示失败不重试

Response

成功响应

text
string
required

转录文本

duration
number

音频总时长(秒)