Text to Speech API for E-Learning and Course Narration

"""
Generate narration audio for every slide in a course manifest.
manifest.json: [{"id": "s01", "lang": "en", "text": "Welcome..."}, ...]
"""
import json, pathlib, requests

API = "https://audexum.com/api/synthesize"
KEY = "sk_..."

slides = json.loads(pathlib.Path("manifest.json").read_text())
out_dir = pathlib.Path("audio")
out_dir.mkdir(exist_ok=True)

VOICE = "F1"   # consistent voice across all slides

for slide in slides:
    dest = out_dir / f"{slide['id']}_{slide['lang']}.mp3"
    if dest.exists():
        continue  # skip already-rendered slides

    r = requests.post(
        API,
        headers={"Authorization": f"Bearer {KEY}"},
        json={
            "text": slide["text"],
            "voice": VOICE,
            "lang": slide["lang"],
            "format": "mp3",
        },
        timeout=60,
    )
    r.raise_for_status()
    dest.write_bytes(r.content)
    print(f"Rendered {dest.name}")

print(f"Done: {len(slides)} slides.")