name: senseaudio-voice-picker description: Recommend the best SenseAudio voice for any scenario or emotion. Use when users ask which voice to use — e.g. "儿童故事播客用什么音色", "电商直播带货适合哪个声音", "我需要撒娇感的女声", "有没有傲娇的音色". No API key needed for recommendations; optionally generates a TTS preview sample. metadata: openclaw: requires: env: - SENSEAUDIO_API_KEY bins: - curl - jq - xxd primaryEnv: SENSEAUDIO_API_KEY homepage: https://senseaudio.cn compatibility: required_credentials: - name: SENSEAUDIO_API_KEY description: Only needed for preview audio. Get from https://senseaudio.cn/platform/api-key env_var: SENSEAUDIO_API_KEY

SenseAudio Voice Picker

Recommend the right voice for any use case. No API call needed — just match the user's description to the best voice IDs.

Voice Library

Free Plan (免费版)

Starter Plan (尝鲜版) — VIP

Advanced/Pro/Business (高级版+) — SVIP

Scenario Matching Guide

Use this to map user descriptions to the right voices:

Recommendation Format

Always show 1–3 options. For each:

**温柔御姐** — female_0006_a
风格：深情
套餐：高级版+（SVIP）
适合：有声书、情感类内容、温柔叙述场景

If the user mentions their plan tier, filter to only show voices they can access.

Optional: TTS Preview

If the user wants to hear a sample, ask for a preview sentence (or use a default like "你好，欢迎体验 SenseAudio 语音服务。"), then call the TTS API:

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\": \"<PREVIEW_TEXT>\",
    \"stream\": false,
    \"voice_setting\": { \"voice_id\": \"<VOICE_ID>\" },
    \"audio_setting\": { \"format\": \"mp3\" }
  }" -o preview.json

jq -r '.data.audio' preview.json | xxd -r -p > preview_<VOICE_ID>.mp3

Generate one file per recommended voice so the user can compare directly.