Echo Agent is a self-hosted, long-running AI agent that connects language models, tools, memory, permissions, and messaging channels in one system. Individuals and teams use it for private automation that retains context across sessions, develops skills, schedules tasks, and requires approval for high-risk actions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fuyuxiang/echo-agent --skill voice-notegit clone --depth 1 https://github.com/fuyuxiang/echo-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fuyuxiang/echo-agent/voice-note)<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/voice-note"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/voice-note/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fuyuxiang/echo-agent/voice-note"><img src="https://agentmods.dev/badge/skills/fuyuxiang/echo-agent/voice-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00611 |
| Opus 5.5 | $0.00012 | $0.00244 |
| Sonnet 5.5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
voice-note scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Voice Note
Speech-to-Text (STT) and Text-to-Speech (TTS) capabilities.
Speech → Text
Option A: OpenAI Whisper API (cloud)
from openai import OpenAI
client = OpenAI()
with open("audio.ogg", "rb") as f:
transcript = client.audio.transcriptions.create(model="whisper-1", file=f)
print(transcript.text)
Option B: faster-whisper (local, no API key)
pip install faster-whisper
from faster_whisper import WhisperModel
model = WhisperModel("base", compute_type="int8") # tiny/base/small/medium/large-v3
segments, info = model.transcribe("audio.ogg", language="zh")
text = " ".join(s.text for s in segments)
print(f"[{info.language}] {text}")
Text → Speech
Edge-TTS (free, excellent Chinese voices)
pip install edge-tts
# CLI
edge-tts --voice zh-CN-XiaoxiaoNeural --text "你好世界" --write-media output.mp3
# List voices
edge-tts --list-voices | grep zh-CN
import edge_tts, asyncio
async def speak(text, voice="zh-CN-XiaoxiaoNeural", output="output.mp3"):
communicate = edge_tts.Communicate(text, voice)
await communicate.save(output)
asyncio.run(speak("今天天气不错，适合出门"))
Chinese Voice Options
| Voice | Style |
|---|---|
| zh-CN-XiaoxiaoNeural | 女声，活泼自然 |
| zh-CN-YunxiNeural | 男声，温和 |
| zh-CN-YunyangNeural | 男声，新闻播报 |
| zh-CN-XiaoyiNeural | 女声，温柔 |
Script
python3 scripts/voice_process.py transcribe audio.ogg --model base --language zh --output transcript.txt
python3 scripts/voice_process.py summarize meeting.mp3 --model small
Note: TTS (speak/voices) is in the separate tts-voice skill.
Audio Format Notes
- Input formats: ogg, mp3, wav, m4a, webm (Whisper accepts most)
- Output: mp3 (Edge-TTS default)
- Convert:
ffmpeg -i input.ogg output.mp3
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 88 lines · 29 tokens per session scan A 0066a2caedd5
voice-note is a skill published in the GitHub repository fuyuxiang/echo-agent (1,058 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 611 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
context-compression
A guide to shortening the information an agent carries between steps. It explains how to replace large tool outputs and old conversation details with compact, useful summaries while preserving important decisions and constraints.
openlore
Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.
openlore-housekeeping
Audit and maintain a shared OpenLore knowledge repository. Use on a schedule or on request to find stale docs, broken links, unreviewed inbox items, and missing skill coverage, then publish an audit report.