Client Python

Le client Python encapsule les API publiques d’upload et de tâches avec des clients synchrone et asynchrone.

Installation

pip install video-to-text-python

Initialisation

import os

from video_to_text import VideoToTextClient

client = VideoToTextClient(
    api_key=os.environ["VTT_API_KEY"],
)

Transcrire un fichier

from pathlib import Path

task = client.transcriptions.transcribe_file(
    Path("meeting.mp4"),
    language="Auto",
    timestamp_mode="CHUNK",
    transcription_mode="balanced",
    timeout=600,
)

print(task.full_text)

Utilisez precision lorsque la précision est plus importante que le coût en crédits.

Upload et création manuels

upload = client.uploads.create({
    "filename": "meeting.mp4",
    "mimetype": "video/mp4",
})

content = Path("meeting.mp4").read_bytes()
client.uploads.put(upload.upload_url, content, mimetype="video/mp4")

asset = client.uploads.complete(upload.upload_id, {
    "fileKey": upload.file_key,
    "fileUrl": upload.file_url,
    "filename": "meeting.mp4",
    "mimetype": "video/mp4",
    "fileSize": len(content),
})

created = client.tasks.create({
    "assetId": asset.asset_id,
    "language": "Auto",
    "timestampMode": "CHUNK",
    "transcriptionMode": "balanced",
})

result = client.tasks.wait(created.transcript_id)
print(result.full_text)

Client asynchrone

from video_to_text import AsyncVideoToTextClient

async with AsyncVideoToTextClient(
    api_key=os.environ["VTT_API_KEY"],
) as client:
    task = await client.transcriptions.transcribe_file(
        Path("meeting.mp4"),
        transcription_mode="balanced",
    )
    print(task.full_text)

Résultats de tâche

tasks.wait() retourne lorsque la tâche atteint SUCCEEDED. Si la tâche atteint FAILED ou CANCELED, le client lance APIError et utilise show_error comme détail lorsque disponible.

Les détails de tâche incluent full_text, chunks, words, source_duration_ms, result_language, transcription_mode et billed_credits.

Erreurs

from video_to_text import APIError, RateLimitError, UploadError

try:
    task = client.transcriptions.transcribe_file(
        Path("meeting.mp4"),
        transcription_mode="balanced",
    )
except RateLimitError:
    print("Please retry later.")
except UploadError:
    print("The media upload did not complete.")
except APIError as error:
    print(error.error_code, error.problem.detail)

Ressources

Pour le code source, les issues et les contributions, consultez le dépôt GitHub video-to-text-python. Installez la dernière version du package video-to-text-python depuis PyPI.