TTS Synthesis

Basics

• Base URL: https://api.ticos.cn
• Synthesize audio: POST /tts
• List voices: GET /tts

1. Synthesize audio (POST /tts)

Headers

• Content-Type: application/json

Request fields

• text (required): text to synthesize
• voice (optional): voice identifier
• volume_ratio (optional): volume ratio (default 50)
• speed_ratio (optional): speaking speed ratio (default 50)
• pitch_ratio (optional): pitch ratio (default 50)

Request example

{
  "voice": "zh_male_jingqiangkanye_moon_bigtts",
  "text": "Hello, this is an example.",
  "volume_ratio": 50,
  "speed_ratio": 50,
  "pitch_ratio": 50
}

Success response

• 200 OK
• Content-Type: audio/wav
• WAV audio bytes as response body

Error responses

• 400 Bad Request: missing required fields or invalid JSON
• 500 Internal Server Error: server-side processing error

Curl example

curl --location 'https://api.ticos.cn/tts' \
--header 'Content-Type: application/json' \
--data-raw '{
  "voice": "zh_male_jingqiangkanye_moon_bigtts",
  "text": "Hello, this is an example.",
  "volume_ratio": 50,
  "speed_ratio": 50,
  "pitch_ratio": 50
}'

2. List available voices (GET /tts)

Common query parameters

• language: e.g. chinese, english
• gender: male / female
• name: partial match by name
• provider: e.g. baidu, bytedance, aliyun
• tags: tag filter, supports comma-separated values
• all: true returns full fields; default false
• skip: pagination offset (default 0)
• top: page size (default 10)

Response example

{
  "code": 0,
  "message": "Success",
  "data": {
    "speakers": [
      {
        "name": "Voice Name",
        "voice": "voice_id"
      }
    ],
    "speakers_count": 10,
    "total_speakers_count": 500
  }
}

Curl examples

# Top 5 Chinese voices
curl "https://api.ticos.cn/tts?language=chinese&skip=0&top=5"

# All male voices with full fields
curl "https://api.ticos.cn/tts?gender=male&all=true"

# Combined filters: Bytedance + Chinese + male
curl "https://api.ticos.cn/tts?provider=bytedance&language=chinese&gender=male"