Model ID
Put this value in the request body's `model` field — not the display name above.
by other · Speech synthesis: read text aloud with the platform's public voices or a voice you cloned, producing downloadable audio (MP3) that is saved to My Voice-overs.
POST /v1/audio/speechhttps://api.dflop.top/v1curl https://api.dflop.top/v1/audio/speech \
-H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "voice-tts-pro",
"input": "你好,欢迎使用语音合成。",
"async": true
}'
# ⚠️ 同步模式受 CDN 约 100 秒非流式上限约束,长文案会被掐断
# —— 音频照样生成、费用照样产生,但你拿不到。长文案一律 async: true
# voice 可传克隆音色 id 或 GET /v1/audio/voices 里的预设 idcurl https://api.dflop.top/v1/audio/speech/$TASK_ID \
-H "Authorization: Bearer sk-gpushare-xxxxxxxx"
# status 三态:pending / succeeded / failed(失败自动全额退款)
# audio_url 是本平台对象存储的永久公网链接This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.
Billed per input character — counted from the `input` you send, not the length of the generated audio.
Sign in and any personal discount on your account will show up here. Sign in
Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).
Open the workbench404 model_not_foundYou passed the display name instead of the model ID.✗ Speech Synthesis→✓ voice-tts-pro
→ Copy the Model ID at the top of this page
402 quota_exceededInsufficient account balance. All your API keys share one balance.
401 / 403The API key is invalid, or it has a model allowlist that doesn't include this ID.
→ Check the key's status and allowed models
400 invalid_request`input` exceeds the 5,000-character limit.
→ Check your request body against the sample code above
Markdown version of this page (Chinese): /models/voice-tts-pro.md