diff --git a/TOOLS.md b/TOOLS.md index da8c92a..4caba1c 100644 --- a/TOOLS.md +++ b/TOOLS.md @@ -144,6 +144,19 @@ bash scripts/dingtalk_tts.sh "要说的内容" **注意**: duration 参数使用秒(整数),不是毫秒 +## 语音识别(Whisper) + +**命令**: `whisper <音频文件> --language Chinese --model small` + +**支持格式**: AMR, OGG, MP3, WAV 等(ffmpeg 支持的格式) + +**用途**: 用户发来的语音消息 → 用 Whisper 转文字 → 处理回复 + +**示例**: +```bash +whisper /root/.openclaw/workspace-assistant/media/inbound/audio-xxx.ogg --language Chinese --model small +``` + ## ⚠️ 邮件操作安全规则 **只读不删!** 严禁执行任何删除邮件的操作,包括但不限于: diff --git a/audio-1774809727190.json b/audio-1774809727190.json new file mode 100644 index 0000000..adb3479 --- /dev/null +++ b/audio-1774809727190.json @@ -0,0 +1 @@ +{"text": "\u90a3\u4f60\u770b\u770b\u8fd9\u6761\u661f\u671f\u4f60\u80fd\u4e0d\u80fd\u8bc6\u522b\u91cc\u9762\u7684\u5185\u5bb9", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 5.0, "text": "\u90a3\u4f60\u770b\u770b\u8fd9\u6761\u661f\u671f\u4f60\u80fd\u4e0d\u80fd\u8bc6\u522b\u91cc\u9762\u7684\u5185\u5bb9", "tokens": [50364, 4184, 16529, 4200, 5562, 48837, 20682, 16786, 2166, 8225, 28590, 5233, 228, 18453, 15759, 8833, 1546, 34742, 25750, 50614], "temperature": 0.0, "avg_logprob": -0.45115266527448383, "compression_ratio": 0.8769230769230769, "no_speech_prob": 0.17235969007015228}], "language": "Chinese"} \ No newline at end of file diff --git a/audio-1774809727190.srt b/audio-1774809727190.srt new file mode 100644 index 0000000..03774b7 --- /dev/null +++ b/audio-1774809727190.srt @@ -0,0 +1,4 @@ +1 +00:00:00,000 --> 00:00:05,000 +那你看看这条星期你能不能识别里面的内容 + diff --git a/audio-1774809727190.tsv b/audio-1774809727190.tsv new file mode 100644 index 0000000..408180f --- /dev/null +++ b/audio-1774809727190.tsv @@ -0,0 +1,2 @@ +start end text +0 5000 那你看看这条星期你能不能识别里面的内容 diff --git a/audio-1774809727190.txt b/audio-1774809727190.txt new file mode 100644 index 0000000..b292294 --- /dev/null +++ b/audio-1774809727190.txt @@ -0,0 +1 @@ +那你看看这条星期你能不能识别里面的内容 diff --git a/audio-1774809727190.vtt b/audio-1774809727190.vtt new file mode 100644 index 0000000..e239b3d --- /dev/null +++ b/audio-1774809727190.vtt @@ -0,0 +1,5 @@ +WEBVTT + +00:00.000 --> 00:05.000 +那你看看这条星期你能不能识别里面的内容 + diff --git a/media/inbound/audio-1774809727190.amr b/media/inbound/audio-1774809727190.amr new file mode 100644 index 0000000..81c6091 Binary files /dev/null and b/media/inbound/audio-1774809727190.amr differ