Speech›Speech Synthesis (Async)
API Key not detected. Please configure to use debug features.
*Text to synthesize (text)
0/50000
Select Model
*Model (model)
u2-tts
Voice Settings
*Voice (voice_id)
Emotion (emotion)
(Not set)
Volume (volume)[0, 100]
050100
Pitch (pitch)[0, 100]
050100
Audio Settings
Sample Rate (audio_sample_rate)
32000
Output Format (format)
mp3
Channel (channel)
1
Custom Pronunciation
Pronunciation Rule (pronunciation_dict)
Task Info
Task ID-
File ID-
Trace ID-
Status-
Guide
Async long text TTS is suitable for whole books
Choose from system or cloned voices
API Reference
CURL
curl -X POST "https://maas-api.hivoice.cn/v1/audio/speech/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "u2-tts",
  "text": "",
  "voice_setting": {
    "voice_id": "zh-CN-xiaoxiao",
    "volume": 50,
    "pitch": 50
  },
  "audio_setting": {
    "audio_sample_rate": 32000,
    "format": "mp3",
    "channel": 1
  }
}'
Request Body JSON
{
  "model": "u2-tts",
  "text": "",
  "voice_setting": {
    "voice_id": "zh-CN-xiaoxiao",
    "volume": 50,
    "pitch": 50
  },
  "audio_setting": {
    "audio_sample_rate": 32000,
    "format": "mp3",
    "channel": 1
  }
}