语音合成（TTS）

开发中

POST

/v1/audio/stream_speech

根据输入的文本，生成对应的音频

请求参数

Header 参数

Body 参数application/json必填

示例

更多参数请参考官方文档。

音色列表请参考文档

{
    "model": "volcengine/seed-tts-2.0",
    "response_format": "mp3",
    "extra_body": {
        "user": {
            "uid": "123123"
        },
        "req_params": {
            "text": "这是一段测试文本，用于测试字节大模型语音合成http单向流式接口效果。",
            "speaker": "zh_female_vv_uranus_bigtts",
            "audio_params": {
                "format": "mp3",
                "sample_rate": 24000,
                "enable_timestamp": true
            },
            "additions": "{\"disable_markdown_filter\":true}"
        }
    }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.360.cn/v1/audio/stream_speech' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
    "model": "volcengine/seed-tts-2.0",
    "response_format": "mp3",
    "extra_body": {
        "user": {
            "uid": "123123"
        },
        "req_params": {
            "text": "这是一段测试文本，用于测试字节大模型语音合成http单向流式接口效果。",
            "speaker": "zh_female_vv_uranus_bigtts",
            "audio_params": {
                "format": "mp3",
                "sample_rate": 24000,
                "enable_timestamp": true
            },
            "additions": "{\"disable_markdown_filter\":true}"
        }
    }
}'

返回响应

🟢200成功

text/event-stream

Bodytext/event-stream

示例

{
  "code": 0,
  "message": "OK",
  "data": "<base64 encoded audio chunk>",
  "sentence": {
    "phonemes": [],
    "text": "你好，语音测试",
    "words": [
      {
        "confidence": 0.89597625,
        "endTime": 0.335,
        "startTime": 0.195,
        "word": "你"
      },
      {
        "confidence": 0.9182152,
        "endTime": 0.725,
        "startTime": 0.335,
        "word": "好，"
      },
      {
        "confidence": 0.51327276,
        "endTime": 1.025,
        "startTime": 0.985,
        "word": "语"
      },
      {
        "confidence": 0.78543895,
        "endTime": 1.205,
        "startTime": 1.025,
        "word": "音"
      },
      {
        "confidence": 0.846961,
        "endTime": 1.395,
        "startTime": 1.205,
        "word": "测"
      },
      {
        "confidence": 0.96582335,
        "endTime": 1.695,
        "startTime": 1.395,
        "word": "试"
      }
    ]
  },
  "usage": {
    "text_words": 7
  }
}

修改于 2026-09-20 07:32:11

语音识别（ASR）

知识库