Text-to-speech (音声合成) の実装

import base64
import json
import struct
import wave
import requests

url = "https://your-sambanova-base-url/v1/audio/speech"
headers = {
    "Authorization": "Bearer your-sambanova-api-key",
    "Content-Type": "application/json",
}
payload = {
    "model": "qwen3-tts",
    "input": "Hello, welcome to SambaNova.",
    "voice": "serena",
    "language": "english",
    "stream": True,
}

pcm_frames = []

with requests.post(url, headers=headers, json=payload, stream=True) as resp:
    resp.raise_for_status()
    for line in resp.iter_lines():
        if not line or not line.startswith(b"data: "):
            continue
        data = line[len(b"data: "):]
        if data == b"[DONE]":
            break
        event = json.loads(data)
        if event.get("finish_reason") == "error":
            raise RuntimeError(f"Stream error: {event.get('error')}")
        audio_b64 = event.get("audio_b64", "")
        if audio_b64:
            pcm_frames.append(base64.b64decode(audio_b64))
        if event.get("finish_reason") == "stop":
            break

# Write f32le PCM frames to a WAV file
pcm_bytes = b"".join(pcm_frames)
num_samples = len(pcm_bytes) // 4  # 4 bytes per f32 sample
samples = struct.unpack(f"{num_samples}f", pcm_bytes)
pcm_int16 = bytes(
    struct.pack("<h", max(-32768, min(32767, int(s * 32767)))) for s in samples
)

with wave.open("output.wav", "wb") as wf:
    wf.setnchannels(1)
    wf.setsampwidth(2)  # 16-bit
    wf.setframerate(24000)
    wf.writeframes(pcm_int16)

print("Saved output.wav")

# This command shows the raw SSE stream. Use the Python example to produce a playable audio file.
curl -X POST https://your-sambanova-base-url/v1/audio/speech \
  -H "Authorization: Bearer your-sambanova-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-tts",
    "input": "Hello, welcome to SambaNova.",
    "voice": "serena",
    "language": "english",
    "stream": true
  }'