Аудио в текст — Транскрибируйте любую запись

# Transcribe a recording (MP3, WAV, M4A, OGG, FLAC, WebM)
curl -X POST https://api.parsejet.com/v1/parse/audio \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F "language=en" \
  -F "with_timestamps=true"

# Response: text + metadata.segments [{start, end, text}] + metadata.words

import httpx

resp = httpx.post(
    "https://api.parsejet.com/v1/parse/audio",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("interview.mp3", "rb")},
    data={"with_timestamps": "true"},
    timeout=600,
)
data = resp.json()
print(data["text"])                       # the transcript
for seg in data["metadata"]["segments"]:  # timed segments for captions
    print(f'{seg["start"]:.1f}s  {seg["text"]}')

const formData = new FormData();
formData.append("file", audioFile); // MP3, WAV, M4A, OGG, FLAC, WebM
formData.append("with_timestamps", "true");

const res = await fetch("https://api.parsejet.com/v1/parse/audio", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY" },
  body: formData,
});
const { text, metadata } = await res.json();
console.log(text, metadata.segments);