Cliente Python

O cliente Python encapsula as APIs públicas de upload e tarefas com clientes síncrono e assíncrono.

Instalação

pip install video-to-text-python

Inicialização

import os

from video_to_text import VideoToTextClient

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

Transcrever um arquivo

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)

Use precision quando a precisão for mais importante que o custo em créditos.

Upload e criação manual

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)

Cliente assíncrono

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)

Resultados da tarefa

tasks.wait() retorna quando a tarefa chega a SUCCEEDED. Se a tarefa chegar a FAILED ou CANCELED, o cliente lança APIError e usa show_error como detalhe quando disponível.

Os detalhes da tarefa incluem full_text, chunks, words, source_duration_ms, result_language, transcription_mode e billed_credits.

Erros

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)

Recursos

Para código-fonte, issues e contribuições, acesse o repositório GitHub video-to-text-python. Instale a versão mais recente do pacote video-to-text-python pelo PyPI.