STT 語音轉文字

curl https://aihubmix.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-large-v3" \
  -F response_format="text" \
  -F temperature="0.2"

curl https://aihubmix.com/v1/audio/translations \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@/path/to/file/audio.mp3" \
  -F model="whisper-large-v3" \
  -F prompt="autocorrect, clean up the stammer, and translate to english" \
  -F response_format="text" \
  -F temperature="0.2"

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # 替換為你的 AiHubMix API 金鑰
  base_url="https://aihubmix.com/v1"
)

# 開啟音訊檔案
audio_file = open("path/to/audio.mp3", "rb")

# 轉錄音訊
transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  language="zh",  # 指定中文以提高準確性
  prompt="Please transcribe the audio accurately, paying attention to punctuation and grammar.",
  response_format="text",
  temperature=0.2  # 降低隨機性以減少幻覺
)

print(transcript)

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # 替換為你的 AiHubMix API 金鑰
  base_url="https://aihubmix.com/v1"
)

# 開啟音訊檔案
audio_file = open("path/to/audio.m4a", "rb")

# 翻譯音訊為英文
translation = client.audio.translations.create(
  model="whisper-large-v3",
  file=audio_file,
  prompt="autocorrect, clean up the stammer, and translate to english",
  response_format="text",
  temperature=0.2
)

print(translation)

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # 替換為你的 AiHubMix API 金鑰
  base_url="https://aihubmix.com/v1"
)

audio_file = open("path/to/audio.wav", "rb")

# 獲取詳細的轉錄結果，包含時間戳
transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  response_format="verbose_json",
  timestamp_granularities=["word"],
  temperature=0.2
)

# 輸出包含單字級時間戳的結果
print(f"Text: {transcript.text}")
print(f"Language: {transcript.language}")
for word in transcript.words:
    print(f"'{word.word}' at {word.start}s - {word.end}s")

from openai import OpenAI
import os

client = OpenAI(
  api_key="sk-***", # 替換為你的 AiHubMix API 金鑰
  base_url="https://aihubmix.com/v1"
)

audio_file = open("path/to/video_audio.mp4", "rb")

# 生成 SRT 字幕檔案
srt_transcript = client.audio.transcriptions.create(
  model="whisper-large-v3",
  file=audio_file,
  response_format="srt",
  language="zh",
  temperature=0.2
)

# 儲存為 .srt 檔案
with open("subtitles.srt", "w", encoding="utf-8") as f:
    f.write(srt_transcript)

print("SRT 字幕檔案已生成")