中英混杂语音识别 API
专为 code-switching 优化
传统语音识别在中英混杂时表现很差:
Whisper + LLM 双引擎处理:
# Python 示例
import requests
response = requests.post(
"https://api.bilingualvoice.com/transcribe",
headers={"Authorization": "Bearer YOUR_API_KEY"},
files={"file": open("meeting.mp3", "rb")}
)
result = response.json()
print(result["corrected_transcription"])
# "今天我们来讨论 machine learning..."