telegram-voice-transcribeTelegram语音转录

Transcribe Telegram voice messages and audio notes into text using the OpenAI Whisper API. Use when (1) a user sends a voice message or audio note via Telegram and you need to read or understand its content, (2) you receive a message with a voice file_id in the Telegram message metadata, (3) the user explicitly asks you to transcribe an audio file. Produces the transcript as plain text so you can respond naturally. Requires OPENAI_API_KEY env var and optionally TELEGRAM_BOT_TOKEN for file_id mod

作者: admin | 来源: ClawHub

telegram-voice-transcribe

Transcribe Telegram voice notes into text via OpenAI Whisper (whisper-1).

Quick Workflow

1. Detect a voice message: look for voice.file_id or audio.file_id in the inbound message metadata.
Run the transcription script:

   python3 ~/openclaw/skills/telegram-voice-transcribe/scripts/transcribe.py \
     --file-id <file_id> --language es

3. Read the JSON output — transcript field contains the text.
Respond to the user based on the transcript content (treat it like typed text).

Script Modes

Mode	Flag	When to use
Telegram file_id	INLINECODE4	Standard case — voice message in Telegram
Local file

Always pass --language es for Spanish speakers to improve speed and accuracy.

Output

CODEBLOCK1

If error key is present, surface it to the user and check setup.

Environment Requirements

- OPENAI_API_KEY — required (set via openclaw configure)
INLINECODE11 — required for --file-id mode

See references/setup.md for full setup, hooks integration, costs, and local Whisper alternative.

Error Handling

Error	Fix
INLINECODE13	Configure key via INLINECODE14
INLINECODE15

telegram-voice-transcribe

通过OpenAI Whisper（whisper-1）将Telegram语音消息转录为文本。

快速工作流程

1. 检测语音消息：在接收消息的元数据中查找voice.fileid或audio.fileid。
运行转录脚本：

bash python3 ~/openclaw/skills/telegram-voice-transcribe/scripts/transcribe.py \ --file-id --language es

3. 读取JSON输出——transcript字段包含文本内容。
根据转录内容回复用户（将其视为输入文本处理）。

脚本模式

模式	参数	使用场景
Telegram file_id	--file-id <id>	标准情况——Telegram中的语音消息
本地文件

对于西班牙语用户，始终传递--language es参数以提高速度和准确性。

输出

json
{transcript: Hola, necesito que hagas un cambio en el juego, language: es, duration_s: 4.2}

如果输出中包含error键，请向用户显示错误信息并检查配置。

环境要求

- OPENAIAPIKEY——必需（通过openclaw configure设置）
TELEGRAMBOTTOKEN——--file-id模式必需

完整配置、钩子集成、成本及本地Whisper替代方案请参见references/setup.md。

错误处理

错误	解决方法
OPENAIAPIKEY not set	通过openclaw configure --section env配置密钥
TELEGRAMBOTTOKEN required

telegram-voice-transcribeTelegram语音转录