undefined

The comparison page includes:
- **Filterable table** — filter by free, SSML, voice cloning, streaming, dialects, multilingual
- **Per-provider detail panels** — cost, max chars/duration, clone method, emotion, languages
- **Voice cards** — recommended voices with style descriptions and best-use labels
- **API key links** — direct links to each provider's console for key acquisition

This page is auto-generated from `data/providers.json` (the single source of truth
for all provider/voice data). Run `python3 scripts/build_docs.py` to regenerate it
after editing the JSON. The same data is queryable on the CLI via
`python3 scripts/tts.py schema backends|voices` (see Schema Introspection).

**After opening the page**, ask the user which backend and voice they'd like to use,
then proceed to Step 2.

undefined

Rules the agent MUST follow:
- MiniMax creation is paid — never run `clone create --platform minimax`
  without the user's explicit confirmation (the CLI enforces `--yes`).
- Only clone the user's own voice or one they are authorized to use — both
  platforms contractually prohibit cloning third parties without consent.
- Reference audio: clean single-speaker speech, no BGM, 10-20s is ideal.
- Named voices live in `~/.ttscn.json` under `cloned_voices`.

Other platforms (Doubao/Tencent/Baidu/Xunfei/Azure) support cloning via
their consoles — the resulting voice id also works as a plain `--voice`.

undefined

undefined

python3 scripts/tts.py --input script.txt output.wav

undefined

undefined

undefined

undefined

python3 scripts/tts.py --list

python3 scripts/tts.py --platform azure \
  "大家好。[PAUSE:0.8] 今天我们聊一个新话题。" out.wav

MINIMAX_MODEL=speech-2.8-hd python3 scripts/tts.py --platform minimax \
  "这也太好笑了 (laughs) 好，我们继续。" out.wav

{
  "_comment": "pronunciation overrides for bank-themed script",
  "行长": "hang2 zhang3",
  "重庆": "chóng qìng"
}

python3 scripts/tts.py --platform azure --phonemes phonemes.json \
  "行长在重庆开会。" out.wav

undefined

System requirement: `ffmpeg`

undefined

Get API Keys:
- Volcano Ark: https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
- DashScope: https://bailian.console.aliyun.com/
- Azure: https://portal.azure.com/
- Tencent Cloud: https://console.cloud.tencent.com/tts
- Baidu AI: https://console.bce.baidu.com/ai/#/ai/speech/overview
- MiniMax: https://platform.minimaxi.com
- Xunfei: https://www.xfyun.cn
- ElevenLabs: https://elevenlabs.io/app/settings/api-keys
- OpenAI: https://platform.openai.com/api-keys
- Google Cloud: https://console.cloud.google.com/apis/credentials

{
  "backend": "minimax",
  "voice": "female-shaonv",
  "rate": "+10%"
}

python3 scripts/tts.py \
  "人工智能正在改变我们的生活方式，从智能助手到自动驾驶，技术革新无处不在。" \
  ai_narration.wav

python3 scripts/tts.py \
  --platform doubao --voice BV001_streaming --rate +10% \
  "家人们，今天给大家推荐一个超好用的神器！" \
  douyin_style.wav

python3 scripts/tts.py \
  --platform cosyvoice --voice longxiaoxia_v3 \
  --input chapter1.txt chapter1.wav

TENCENT_SECRET_ID="xxx" TENCENT_SECRET_KEY="xxx" \
python3 scripts/tts.py \
  --platform tencent --voice 101001 \
  --input course_script.txt course_audio.wav

MINIMAX_API_KEY="xxx" \
python3 scripts/tts.py \
  --platform minimax --voice female-shaonv \
  "这是一段充满感情的语音合成演示。" premium.wav

undefined

undefined

// Success
{"ok":true, "data":{...}, "meta":{"version":"...","schema_version":"1.2.0","timestamp":"...","ms":123}}

// Error
{"ok":false, "error":{"code":"auth_missing_env","message":"set one of: VOLCENGINE_APPID+VOLCENGINE_ACCESS_TOKEN / VOLCENGINE_API_KEY","retryable":false,"field":"VOLCENGINE_APPID","backend":"doubao"}, "meta":{...}}

{"ok":true, "data":{
  "output_file": "out.wav",
  "word_boundaries": [
    {"text": "你好", "offset_sec": 0.1,   "duration_sec": 0.45},
    {"text": "世界", "offset_sec": 0.562, "duration_sec": 0.5}
  ]
}}

python3 scripts/tts.py schema backends              # All 11 backends (compact by default)
python3 scripts/tts.py schema backends --full       # All fields (22 per backend)
python3 scripts/tts.py schema backends.doubao       # Single backend full detail
python3 scripts/tts.py schema voices                # All voice presets per backend
python3 scripts/tts.py schema tags                  # Tag definitions
python3 scripts/tts.py schema version               # Version + providers data freshness

undefined

undefined

A cache hit returns the stored result with `data.cached: true`. If the cached
`output_file` no longer exists on disk, the call **re-synthesizes** instead of
returning a stale success.

undefined

undefined