text2speech（text2speech 控制）

SenseAudio Text-to-Speech (TTS)

SenseAudio TTS converts text to natural, emotionally rich speech using a large language model. Supports 10+ emotions, streaming output (SSE), and fine-grained voice control.

Endpoint: POST https://api.senseaudio.cn/v1/t2a_v2 Auth: Authorization: Bearer $SENSEAUDIO_API_KEY Max text length: 10,000 characters

Request Parameters

Headers

Body

voice_setting

audio_setting

<break> Pause Tag

Insert pauses in text:

你好<break time=500>欢迎使用我们的服务

• time unit: milliseconds, min 100ms

Non-Streaming Response

{
  "data": {
    "audio": "hex-encoded audio data...",
    "status": 2
  },
  "extra_info": {
    "audio_length": 3500,
    "audio_sample_rate": 32000,
    "audio_size": 56000,
    "bitrate": 128000,
    "audio_format": "mp3",
    "audio_channel": 1,
    "word_count": 24,
    "usage_characters": 30
  },
  "base_resp": {"status_code": 0, "status_msg": "success"}
}

data.audio is hex-encoded. Decode: bytes.fromhex(audio_hex)

SSE Streaming Response

Each chunk: data: {"data":{"audio":"hex...","status":1},...}

Final chunk has status: 2 and includes extra_info.

Code Examples

curl (non-streaming)

curl -X POST https://api.senseaudio.cn/v1/t2a_v2 \
  -H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "SenseAudio-TTS-1.0",
    "text": "道可道，非常道。名可名，非常名。",
    "stream": false,
    "voice_setting": {"voice_id": "male_0004_a"}
  }' -o response.json

jq -r '.data.audio' response.json | xxd -r -p > output.mp3

Python (non-streaming)

import requests

resp = requests.post(
    "https://api.senseaudio.cn/v1/t2a_v2",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "SenseAudio-TTS-1.0",
        "text": "道可道，非常道。",
        "stream": False,
        "voice_setting": {"voice_id": "male_0004_a"}
    }
)
result = resp.json()
audio_bytes = bytes.fromhex(result["data"]["audio"])
with open("output.mp3", "wb") as f:
    f.write(audio_bytes)

Python (SSE streaming)

import requests, json

with requests.post(
    "https://api.senseaudio.cn/v1/t2a_v2",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={"model": "SenseAudio-TTS-1.0", "text": "这是流式输出示例。", "stream": True,
          "voice_setting": {"voice_id": "male_0004_a"}},
    stream=True
) as r:
    with open("output.mp3", "wb") as f:
        for line in r.iter_lines():
            if line:
                line_str = line.decode("utf-8")
                if line_str.startswith("data: "):
                    chunk = json.loads(line_str[6:])
                    if chunk.get("data", {}).get("audio"):
                        f.write(bytes.fromhex(chunk["data"]["audio"]))

SenseAudio 文本转语音（TTS）

SenseAudio TTS 基于千亿参数大模型，将文字转化为自然流畅、情感丰富的语音。支持 10+ 种情感、流式输出（SSE）及精细化语音控制。

接口地址： POST https://api.senseaudio.cn/v1/t2a_v2 鉴权： Authorization: Bearer $SENSEAUDIO_API_KEY 最大文本长度： 10,000 字符

请求参数

请求头

请求体

voice_setting（音色设置）

audio_setting（音频设置）

<break> 停顿符

在文本中插入停顿：

你好<break time=500>欢迎使用我们的服务

• time 单位为毫秒，最小值 100ms

非流式响应

{
  "data": {"audio": "hex编码音频...", "status": 2},
  "extra_info": {
    "audio_length": 3500,
    "audio_sample_rate": 32000,
    "audio_size": 56000,
    "audio_format": "mp3",
    "word_count": 24,
    "usage_characters": 30
  },
  "base_resp": {"status_code": 0, "status_msg": "success"}
}

data.audio 为 hex 编码，解码：bytes.fromhex(audio_hex)

SSE 流式响应

每个数据块：data: {"data":{"audio":"hex...","status":1},...}

最后一个 chunk status: 2，包含完整 extra_info。

代码示例

curl（非流式）

curl -X POST https://api.senseaudio.cn/v1/t2a_v2 \
  -H "Authorization: Bearer $SENSEAUDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "SenseAudio-TTS-1.0",
    "text": "道可道，非常道。名可名，非常名。",
    "stream": false,
    "voice_setting": {"voice_id": "male_0004_a"}
  }' -o response.json

jq -r '.data.audio' response.json | xxd -r -p > output.mp3

Python（非流式）

import requests

resp = requests.post(
    "https://api.senseaudio.cn/v1/t2a_v2",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "model": "SenseAudio-TTS-1.0",
        "text": "道可道，非常道。",
        "stream": False,
        "voice_setting": {"voice_id": "male_0004_a"}
    }
)
audio_bytes = bytes.fromhex(resp.json()["data"]["audio"])
open("output.mp3", "wb").write(audio_bytes)