语音模型接入

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_STEP_API_KEY",
    base_url="https://api.stepfun.com/step_plan/v1",
)

response = client.audio.speech.create(
    model="stepaudio-2.5-tts",
    input="今天天气不错，适合出去走走。",
    voice="cixingnansheng",
    extra_body={
        "instruction": "语气温柔，语速偏慢",
    },
)

response.stream_to_file("speech.mp3")

import websocket
import rel
import json

headers = {
    "Authorization": "Bearer YOUR_STEP_API_KEY"
}

def get_start_event(sid):
    return json.dumps({
        "type": "tts.create",
        "data": {
            "session_id": sid,
            "voice_id": "cixingnansheng",
            "response_format": "wav",
            "volume_ratio": 1.0,
            "speed_ratio": 1.0,
            "sample_rate": 16000,
            "instruction": "语气温柔，语速偏慢"
        },
    })

def on_message(ws, message):
    data = json.loads(message)
    session_id = data["data"]["session_id"]
    event_type = data["type"]

    if event_type == "tts.connection.done":
        ws.send(get_start_event(session_id))

    print(message)

def on_error(ws, error):
    print(error)

if __name__ == "__main__":
    ws = websocket.WebSocketApp(
        # Step Plan 使用 /step_plan/v1 路径
        "wss://api.stepfun.com/step_plan/v1/realtime/audio?model=stepaudio-2.5-tts",
        header=headers,
        on_message=on_message,
        on_error=on_error,
    )

    ws.run_forever(dispatcher=rel, reconnect=5)
    rel.signal(2, rel.abort)
    rel.dispatch()