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 Approaching-AI/AIMA --skill aima-ttsgit clone --depth 1 https://github.com/Approaching-AI/AIMAWrote 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/approaching-ai/aima/aima-tts)<a href="https://agentmods.dev/skills/approaching-ai/aima/aima-tts"><img src="https://agentmods.dev/badge/skills/approaching-ai/aima/aima-tts/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/approaching-ai/aima/aima-tts"><img src="https://agentmods.dev/badge/skills/approaching-ai/aima/aima-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 19 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00025 | $0.00462 |
| Opus 5.5 | $0.00010 | $0.00185 |
| Sonnet 5.5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
aima-tts scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"openclaw":{"emoji":"🔊","requires":{"bins":["curl"]},"always":true}} What it actually says
AIMA Text-to-Speech
Generate speech audio from text using the TTS model currently managed by AIMA/OpenClaw.
When to use
- The user explicitly asks for a spoken or voice reply.
- The user asks you to say something aloud instead of only writing it.
- The user wants a short audio clip in Chinese or English.
Required behavior
- Write a short spoken script first.
- Run
{baseDir}/scripts/speak.shwith that script. - After OpenClaw attaches the generated media, reply with exactly
NO_REPLY. - If TTS generation fails, give a brief text fallback that says the audio conversion failed.
- Keep the spoken script short and in the user's language unless they ask for something longer.
Quick start
{baseDir}/scripts/speak.sh "你好世界" --filename hello.wav
Useful flags
{baseDir}/scripts/speak.sh "今天天气真好" --filename weather.wav
{baseDir}/scripts/speak.sh "Hello AIMA" --filename greeting.wav --voice default
{baseDir}/scripts/speak.sh "请用参考音色说这句话" --api tts --reference-audio /tmp/ref.wav --reference-text "参考文案"
Output
- WAV audio file saved to workspace
MEDIA:line printed for OpenClaw auto-attachment
Notes
- Model: auto-detected from
~/.openclaw/openclaw.json(override withAIMA_TTS_MODEL) - Voice:
default(single voice) - API:
speech(/v1/audio/speech) ortts(/v1/tts) - Output format: configurable with
--response-format - Optional reference fields:
--reference-audio,--reference-text - Runs on AIMA proxy at
http://127.0.0.1:6188/v1
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.
- 2mo ago First seen · 52 lines · 25 tokens per session scan A d4c981f7090a
aima-tts is a skill published in the GitHub repository Approaching-AI/AIMA (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 462 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
olares-router
Olares models via olares-cli router — Router (the AI gateway) and the Model Console inside a locally installed model application. Configure cloud vendors and their models, manage local LLM / embedding / audio / OCR model applications, edit a local model's card, name models with aliases, groups and default categories…
on-device-verification
Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization…
accuracy-safe-quantization
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long…
gpu-clean-conversion
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
litert-conversion-workflow
Convert a Hugging Face LLM or vision-language model checkpoint into a .litertlm bundle that runs on the LiteRT-LM runtime with verified quality - classify the architecture against known runtime walls, pick the recipe family (dense, reasoning, hybrid SSM, VLM), export, quantize, gate the result against the source…
litert-runtime
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite task, including Gradle setup, image classification or vision/audio/embedding helpers, TensorBuffer reuse, CPU memory optimization, Bitmap…