← 返回 Skills 市场

Telegram Voice STT (Windows)

Name: Telegram Voice STT (Windows)
Author: aditya0320

作者 Aditya Singh · GitHub ↗ · v1.0.0 · MIT-0

win32 ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install telegram-voice-stt

功能描述

Transcribe Telegram voice notes to text before the assistant replies. Use when the user sends a voice message on Telegram (@AadiAssistantbot), or mentions vo...

使用说明 (SKILL.md)

\r \r

Telegram Voice → Text (STT)\r

\r When a user sends a voice note on Telegram, OpenClaw transcribes it before the model runs.\r \r

How it works\r

Telegram delivers .ogg voice file to .openclaw/media/inbound/\r
Gateway runs transcribe-audio-cli.js (Google Cloud Speech-to-Text)\r
Transcript replaces \x3Cmedia:audio> in the user message\r
Optional echo: user sees 📝 Heard: "..." in Telegram\r
Assistant answers the transcribed text via Bifrost → genapp-proxy → Dialogflow\r \r

Rules for the assistant\r

Never say "I cannot process audio" if a transcript is present\r
Reply to the transcript content as the user's actual question\r
For Hindi/English mix, answer in the language the user spoke or ask which they prefer\r
If transcription is empty, ask the user to type their message or re-record\r \r

Stack\r

OpenClaw: tools.media.audio CLI model → ~/.openclaw/gcp/transcribe-audio-cli.js\r
Fallback: genapp-proxy also transcribes voice before Dialogflow (8192 token limit)\r \r

Manual test (gateway machine)\r

node "$env:USERPROFILE\.openclaw\gcp	ranscribe-audio-cli.js" "C:\path	o\voice.ogg"\r
```\r

安全使用建议

Install only if you are comfortable with Telegram voice notes being sent through Google Cloud and related OpenClaw/Dialogflow infrastructure for transcription and response handling. Use a limited service account, avoid sensitive voice content unless your retention and consent requirements are met, and consider tightening the trigger wording before broad deployment.

能力评估

✓ Purpose & Capability

The artifact consistently describes one purpose: transcribing Telegram .ogg voice notes before the assistant replies, then treating the transcript as the user's message.

ℹ Instruction Scope

The trigger text is broader than strict Telegram voice-note handling because it also mentions generic STT/audio-to-text phrases, but the runtime rules remain focused on transcript handling and do not request unrelated actions.

✓ Install Mechanism

The inspected package contains only SKILL.md; no install script, binary, bundled code, or automatic setup mechanism is present.

ℹ Credentials

GOOGLE_APPLICATION_CREDENTIALS and GOOGLE_CLOUD_PROJECT are proportionate for Google Speech-to-Text, but users should use narrowly scoped credentials because voice audio and transcripts may be processed by external cloud services.

✓ Persistence & Privilege

No persistence mechanism, background worker, privilege escalation, credential harvesting, local indexing, deletion, or mutation authority is included in the artifact.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install telegram-voice-stt
安装完成后，直接呼叫该 Skill 的名称或使用 /telegram-voice-stt 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Auto-transcribe Telegram voice notes via Google Speech-to-Text

元数据

Slug telegram-voice-stt

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题