Azure 语音转文本 REST API Python 实现
Azure 语音转文本 REST API (短音频)
一个简单的 REST API,用于短音频文件(最多 60 秒)的语音转文本转录。无需 SDK,仅需 HTTP 请求。
前置条件
1. Azure 订阅 - 免费创建
2. 语音资源 - 在 Azure 门户 中创建
3. 获取凭据 - 部署后,前往 资源 > 密钥和终结点
环境变量
# 必填
AZURE_SPEECH_KEY=<your-speech-resource-key>
AZURE_SPEECH_REGION=<region> # 例如 eastus, westus2, westeurope
备选:直接使用终结点
AZURE_SPEECH_ENDPOINT=https://<region>.stt.speech.microsoft.com安装
pip install requests快速上手
import os
import requests
def transcribe_audio(audio_file_path: str, language: str = "en-US") -> dict:
"""使用 REST API 转录短音频文件(最多 60 秒)。"""
region = os.environ["AZURE_SPEECH_REGION"]
api_key = os.environ["AZURE_SPEECH_KEY"]
url = f"https://{region}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1"
headers = {
"Ocp-Apim-Subscription-Key": api_key,
"Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000",
"Accept": "application/json"
}
params = {
"language": language,
"format": "detailed" # 或 "simple"
}
with open(audio_file_path, "rb") as audio_file:
response = requests.post(url, headers=headers, params=params, data=audio_file)
response.raise_for_status()
return response.json()
使用示例
result = transcribe_audio("audio.wav", "en-US")
print(result["DisplayText"])音频要求
| 格式 | 编解码器 | 采样率 | 备注 |
|--------|-------|-------------|-------|
| WAV | PCM | 16 kHz, 单声道 | 推荐 |
| OGG | OPUS | 16 kHz, 单声道 | 文件体积更小 |
限制条件:
- 音频最长 60 秒
- 发音评估:最长 30 秒
- 不支持部分/中间结果(仅返回最终结果)
Content-Type 请求头
# WAV PCM 16kHz
"Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000"
OGG OPUS
"Content-Type": "audio/ogg; codecs=opus"响应格式
简单格式 (默认)
params = {"language": "en-US", "format": "simple"}{
"RecognitionStatus": "Success",
"DisplayText": "Remind me to buy 5 pencils.",
"Offset": "1236645672289",
"Duration": "1236645672289"
}详细格式
params = {"language": "en-US", "format": "detailed"}{
"RecognitionStatus": "Success",
"Offset": "1236645672289",
"Duration": "1236645672289",
"NBest": [
{
"Confidence": 0.9052885,
"Display": "What's the weather like?",
"ITN": "what's the weather like",
"Lexical": "what's the weather like",
"MaskedITN": "what's the weather like"
}
]
}分块传输 (推荐)
为了降低延迟,可以分块流式传输音频:
import os
import requests
def transcribe_chunked(audio_file_path: str, language: str = "en-US") -> dict:
"""分块流式传输音频以降低延迟"""
wer 延迟。"""
region = os.environ["AZURE_SPEECH_REGION"]
api_key = os.environ["AZURE_SPEECH_KEY"]
url = f"https://{region}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1"
headers = {
"Ocp-Apim-Subscription-Key": api_key,
"Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000",
"Accept": "application/json",
"Transfer-Encoding": "chunked",
"Expect": "100-continue"
}
params = {"language": language, "format": "detailed"}
def generate_chunks(file_path: str, chunk_size: int = 1024):
with open(file_path, "rb") as f:
while chunk := f.read(chunk_size):
yield chunk
response = requests.post(
url,
headers=headers,
params=params,
data=generate_chunks(audio_file_path)
)
response.raise_for_status()
return response.json()
## 身份验证选项
选项 1:订阅密钥(简单)
### 选项 2:Bearer 令牌def get_access_token() -> str:
"""从令牌端点获取访问令牌。"""
region = os.environ["AZURE_SPEECH_REGION"]
api_key = os.environ["AZURE_SPEECH_KEY"]
token_url = f"https://{region}.api.cognitive.microsoft.com/sts/v1.0/issueToken"
response = requests.post(
token_url,
headers={
"Ocp-Apim-Subscription-Key": api_key,
"Content-Type": "application/x-www-form-urlencoded",
"Content-Length": "0"
}
)
response.raise_for_status()
return response.text
在请求中使用令牌(有效期 10 分钟)
token = get_access_token() headers = { "Authorization": f"Bearer {token}", "Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000", "Accept": "application/json" }## 查询参数
| 参数 | 必填 | 取值 | 描述 |
|-----------|----------|--------|-------------|
| language | 是 | en-US, de-DE 等 | 语音语言 |
| format | 否 | simple, detailed | 结果格式(默认:simple) |
| profanity | 否 | masked, removed, raw | 脏话处理(默认:masked) |
识别状态值
| 状态 | 描述 |
|--------|-------------|
| Success | 识别成功 |
| NoMatch | 检测到语音但未匹配到词汇 |
| InitialSilenceTimeout | 仅检测到静音 |
| BabbleTimeout | 仅检测到噪音 |
| Error | 内部服务错误 |
脏话处理
使用星号掩盖脏话(默认)
params = {"language": "en-US", "profanity": "masked"}完全移除脏话
params = {"language": "en-US", "profanity": "removed"}原样保留脏话
params = {"language": "en-US", "profanity": "raw"}## 错误处理def transcribe_with_error_handling(audio_path: str, language: str = "en-US") -> dict | None:
"""带有适当错误处理的转录函数。"""
region = os.environ["AZURE_SPEECH_REGION"]
api_key = os.environ["AZURE_SPEECH_KEY"]
url = f"https://{region}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1"
try:
with open(audio_path, "rb") as audio_file:
response = requests.post(
url,
headers={
"Ocp-Apim-Subscrip
tion-Key": api_key,
"Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000",
"Accept": "application/json"
},
params={"language": language, "format": "detailed"},
data=audio_file
)
if response.status_code == 200:
result = response.json()
if result.get("RecognitionStatus") == "Success":
return result
else:
print(f"Recognition failed: {result.get('RecognitionStatus')}")
return None
elif response.status_code == 400:
print(f"Bad request: Check language code or audio format")
elif response.status_code == 401:
print(f"Unauthorized: Check API key or token")
elif response.status_code == 403:
print(f"Forbidden: Missing authorization header")
else:
print(f"Error {response.status_code}: {response.text}")
return None
except requests.exceptions.RequestException as e:
print(f"Request failed: {e}")
return None异步版本
import os
import aiohttp
import asyncio
async def transcribe_async(audio_file_path: str, language: str = "en-US") -> dict:
"""使用 aiohttp 的异步版本。"""
region = os.environ["AZURE_SPEECH_REGION"]
api_key = os.environ["AZURE_SPEECH_KEY"]
url = f"https://{region}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1"
headers = {
"Ocp-Apim-Subscription-Key": api_key,
"Content-Type": "audio/wav; codecs=audio/pcm; samplerate=16000",
"Accept": "application/json"
}
params = {"language": language, "format": "detailed"}
async with aiohttp.ClientSession() as session:
with open(audio_file_path, "rb") as f:
audio_data = f.read()
async with session.post(url, headers=headers, params=params, data=audio_data) as response:
response.raise_for_status()
return await response.json()
使用示例
result = asyncio.run(transcribe_async("audio.wav", "en-US"))
print(result["DisplayText"])支持的语言
常用语言代码(详见 完整列表):
| 代码 | 语言 |
|------|----------|
| en-US | 英语 (美国) |
| en-GB | 英语 (英国) |
| de-DE | 德语 |
| fr-FR | 法语 |
| es-ES | 西班牙语 (西班牙) |
| es-MX | 西班牙语 (墨西哥) |
| zh-CN | 中文 (普通话) |
| ja-JP | 日语 |
| ko-KR | 韩语 |
| pt-BR | 葡萄牙语 (巴西) |
最佳实践
1. 使用 WAV PCM 16kHz 单声道 以获得最佳兼容性
2. 启用分块传输 (chunked transfer) 以降低延迟
3. 缓存访问令牌 9 分钟(有效期为 10 分钟)
4. 指定正确的语言 以确保识别准确
5. 需要置信度分数时 请使用 detailed 格式
6. 在生产代码中 处理所有 RecognitionStatus 的取值
何时不要使用此 API
在需要以下功能时,请改用 Speech SDK 或 批量转录 API:
- 音频长度超过 60 秒
- 实时流式转录
- 部分/中间结果
- 语音翻译
- 自定义语音模型
- 大量文件的批量转录
参考文件
| 文件 | 内容 |
|------|----------|
| references/pronunciation-assessment.md | 发音评估参数与评分 |
适用场景
此技能适用于 以执行概览中所描述的工作流或操作。局限性
- 仅在任务明确符合上述范围时使用此技能。
- 不要将输出结果视为针对特定环境的验证、测试或专家评审的替代方案。
- 如果缺少必要的输入、权限、安全边界或成功标准,请停止操作并请求澄清。