WhisperX（语音转文字）

正式环境

https://api.302.ai

POST

/302/whisperx

开源版WhsiperX

价格：0.002 PTC/分钟

请求参数

Header 参数

Body 参数multipart/form-data

返回响应

🟢200成功

application/json

Body

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.302.ai/302/whisperx' \
--header 'Authorization: Bearer ' \
--form 'audio_input=@""' \
--form 'language=""' \
--form 'processing_type="align"' \
--form 'translate="false"' \
--form 'output="text"'

响应示例

{
    "usage": {
        "input_audio_length": 68.075125,
        "elapsed_time": 6.5518,
        "inference_type": "alignment"
    },
    "segments": [
        {
            "start": 26.169,
            "end": 47.178,
            "text": " Teksting av Nicolai Winther",
            "words": [
                {
                    "word": "Teksting",
                    "start": 26.169,
                    "end": 36.754,
                    "score": 0.002
                },
                {
                    "word": "av",
                    "start": 36.814,
                    "end": 39.035,
                    "score": 0.0
                },
                {
                    "word": "Nicolai",
                    "start": 39.055,
                    "end": 43.036,
                    "score": 0.001
                },
                {
                    "word": "Winther",
                    "start": 43.056,
                    "end": 47.178,
                    "score": 0.003
                }
            ],
            "speaker": null
        }
    ],
    "subtitles": null,
    "error": null
}

修改于 2026-01-19 06:42:45

Alignments（字幕打轴）

Video-Understanding（视频理解）