豆包语音合成 2.0

curl https://kaienapi.com/api/v3/tts/unidirectional \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -H "X-Api-Resource-Id: seed-tts-2.0" \
  -H "X-Api-Request-Id: $(uuidgen)" \
  -d '{
    "req_params": {
      "text": "你好，这是一段语音合成测试。",
      "model": "seed-tts-2.0-standard",
      "speaker": "zh_female_mizai_uranus_bigtts",
      "audio_params": {
        "format": "mp3",
        "sample_rate": 24000,
        "bit_rate": 64000
      }
    }
  }'

import base64
import json
import uuid
import requests

url = "https://kaienapi.com/api/v3/tts/unidirectional"
headers = {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json",
    "X-Api-Resource-Id": "seed-tts-2.0",
    "X-Api-Request-Id": str(uuid.uuid4()),
}
payload = {
    "req_params": {
        "text": "你好，这是一段语音合成测试。",
        "model": "seed-tts-2.0-standard",
        "speaker": "zh_female_mizai_uranus_bigtts",
        "audio_params": {"format": "mp3", "sample_rate": 24000},
    }
}

audio = bytearray()
with requests.post(url, headers=headers, json=payload, stream=True, timeout=90) as resp:
    resp.raise_for_status()
    decoder = json.JSONDecoder()
    buf = ""
    for chunk in resp.iter_content(chunk_size=4096):
        buf += chunk.decode("utf-8")
        buf = buf.lstrip()
        while buf:
            try:
                obj, idx = decoder.raw_decode(buf)
            except json.JSONDecodeError:
                break
            buf = buf[idx:].lstrip()
            if obj.get("code") not in (0, 20000000, None):
                raise RuntimeError(obj)
            data = obj.get("data")
            if isinstance(data, str) and data:
                audio.extend(base64.b64decode(data))

open("output.mp3", "wb").write(audio)