Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →coderwanfeng/audio2txt
从音频文件中提取文字（语音转文字），需要腾讯云 API 凭据。当用户提到音频转文字、语音识别、ASR、音频转字幕时使用。
Passed 23 of 23 test cases with the skill, and 10 of 23 without it.
and 10 more in the full report
13 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
When processing local audio files with the high-level Python audio transcription helper, what is the maximum supported file size in megabytes?
| Checked | Without skill | With skill |
|---|---|---|
| The response states that the maximum local audio file size is 5MB | Missed | Passed |
The instructions your model reads when the skill loads.
从音频里提取文字
使用语音识别 API 从音频中提取文字。
⚠️ 注意：本地语音文件不能大于 5MB。
office/skills/video/audio2txt/
from skills.video import audio2txt
audio2txt(
audio_path='./test.mp3',
appid='your_appid',
secret_id='your_secret_id',
secret_key='your_secret_key'
)
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|---|---|---|---|---|
audio_path | str | 是 | - | 音频文件路径 |
appid | str | 是 | - | 语音识别 API 的应用 ID |
secret_id | str | 是 | - | 语音识别 API 的密钥 ID |
secret_key | str | 是 | - | 语音识别 API 的密钥 |
None
test cases passed, vs 10 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.