StepAudio 2.5 Realtime

import os
import json
import base64
import wave
import urllib.request
from io import BytesIO
import websocket  # pip install websocket-client

URL = "wss://api.stepfun.ai/v1/realtime?model=stepaudio-2.5-realtime"
SAMPLE_AUDIO_URL = "https://static-openapi.stepfun.ai/static/platform-docs/resource/1782215968301_hza73c.wav"  # sample English customer question (24 kHz mono WAV)

# Download the sample question and read its PCM16 samples (24 kHz, mono).
wav_bytes = urllib.request.urlopen(SAMPLE_AUDIO_URL).read()
with wave.open(BytesIO(wav_bytes), "rb") as wf:
    pcm = wf.readframes(wf.getnframes())

reply = bytearray()

def on_open(ws):
    # Configure the session: respond with text and audio, in English.
    ws.send(json.dumps({
        "type": "session.update",
        "session": {
            "modalities": ["text", "audio"],
            "instructions": "You are a warm, professional customer-support voice agent. Acknowledge how the customer feels, then help. Keep replies short.",
            "voice": "soft-spoken-gentleman",
            "input_audio_format": "pcm16",
            "output_audio_format": "pcm16",
        },
    }))
    # Stream the caller's audio, commit it as a turn, then ask the model to respond.
    audio_b64 = base64.b64encode(pcm).decode()
    for i in range(0, len(audio_b64), 32000):
        ws.send(json.dumps({"type": "input_audio_buffer.append", "audio": audio_b64[i:i + 32000]}))
    ws.send(json.dumps({"type": "input_audio_buffer.commit"}))
    ws.send(json.dumps({"type": "response.create"}))

def on_message(ws, message):
    event = json.loads(message)
    if event["type"] == "conversation.item.input_audio_transcription.completed":
        print("Caller said:", event["transcript"])           # the model's transcript of the input
    elif event["type"] == "response.audio.delta":
        reply.extend(base64.b64decode(event["delta"]))        # streamed PCM16 audio
    elif event["type"] == "response.audio_transcript.done":
        print("Assistant:", event["transcript"])              # text of the spoken reply
    elif event["type"] == "response.done":
        ws.close()

ws = websocket.WebSocketApp(
    URL,
    header=[f"Authorization: Bearer {os.environ['STEPFUN_API_KEY']}"],
    on_open=on_open,
    on_message=on_message,
)
ws.run_forever()

# Save the spoken reply (PCM16, 24 kHz, mono) as a playable WAV file.
with wave.open("reply.wav", "wb") as f:
    f.setnchannels(1)
    f.setsampwidth(2)
    f.setframerate(24000)
    f.writeframes(bytes(reply))