SenseAudio TTS Quick

Zero-config speech synthesis. User gives text, you produce an mp3 file — no API knowledge required.

Voice Selection

Default voice: male_0004_a (儒雅道长, neutral).

Map natural-language requests to voice IDs before calling the API:

If the user names a voice not in this table, use male_0004_a and note the fallback.

Long Text Pacing

For text longer than 100 characters, insert <break time="300"/> after each 。 ！ ？ to improve natural rhythm:

原文：今天天气很好。我们出去走走吧。
处理后：今天天气很好。<break time="300"/>我们出去走走吧。<break time="300"/>

Do not insert breaks inside quoted speech or after mid-sentence punctuation like ，.

API Call

curl -s -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": "<TEXT>",
    "stream": false,
    "voice_setting": {
      "voice_id": "<VOICE_ID>"
    },
    "audio_setting": {
      "format": "mp3"
    }
  }' -o response.json

# Decode hex audio to mp3
jq -r '.data.audio' response.json | xxd -r -p > output.mp3

Check base_resp.status_code == 0 before decoding. On error, show base_resp.status_msg.

Output

After generating the file:

1. Save as a descriptive filename, e.g. speech_<timestamp>.mp3 or based on the first few words of the text.
2. Report:
   • File path
   • Audio duration: jq '.extra_info.audio_length' response.json (ms → seconds)
   • Character count: jq '.extra_info.usage_characters' response.json
   • Voice used

Example output:

生成完成：speech_20240315.mp3
音色：温柔御姐 (female_0006_a)
时长：4.2 秒
字数：38 字

Error Handling