Aliyun TTS

Alibaba Cloud Text-to-Speech synthesis service.

Security Scan

The skill's code and SKILL.md implement an Alibaba Cloud TTS client and request valid Alibaba credentials, but the registry metadata omits required env vars and there are small packaging/instruction mismatches that warrant caution.

Purpose & Capability

The code and SKILL.md implement Alibaba Cloud TTS (signing, token fetch, audio download) which is coherent with the skill name/description. However the registry metadata states 'Required env vars: none' and 'Primary credential: none' while both SKILL.md and the script require ALIYUN_APP_KEY, ALIYUN_ACCESS_KEY_ID and ALIYUN_ACCESS_KEY_SECRET — a metadata/packageing inconsistency.

Instruction Scope

SKILL.md instructs configuring the three ALIYUN_* environment variables and using a CLI at {baseDir}/bin/aliyun-tts. The repository provides aliyun_tts.py (the actual client) but no install script or a bin shim is included — the usage instructions assume a packaged CLI that isn't present. Instructions do not ask for unrelated files or secrets and network calls are to Alibaba NLS endpoints only.

Install Mechanism

No install spec (instruction-only) and a single Python script is included. No remote download or extracts are used, so there is no high-risk install mechanism in the package itself.

Credentials

The three required env vars (App Key, AccessKeyId, AccessKeySecret) are appropriate for an Alibaba TTS client. The concern is that the skill registry metadata did not declare these required credentials — the skill will in practice require and consume a sensitive secret (ALIYUN_ACCESS_KEY_SECRET), which will be stored/managed via the agent's config per SKILL.md.

Persistence & Privilege

The skill is not marked always:true and is user-invocable; it does not request persistent system-wide changes or other skills' credentials. There is no evidence it modifies other skills or global agent settings.

What to consider before installing

This package appears to be a straightforward Alibaba Cloud TTS client (it signs requests and fetches audio) and needs three Alibaba credentials (including a secret). Before installing: 1) Be aware the registry metadata did not declare the required env vars — expect to provide ALIYUN_APP_KEY, ALIYUN_ACCESS_KEY_ID and ALIYUN_ACCESS_KEY_SECRET. 2) The repo includes aliyun_tts.py but no installer or bin shim; verify how the CLI will be installed/registered (SKILL.md refers to {baseDir}/bin/aliyun-tts). 3) Only provide least-privilege Alibaba credentials (use an IAM key with only NLS permissions) and avoid reusing high-privilege keys. 4) Confirm you trust the skill owner before storing ALIYUN_ACCESS_KEY_SECRET in the agent config. 5) If you need higher assurance, review or run the Python script in a controlled environment and check network destinations (nls-meta.<region>.aliyuncs.com and nls-gateway-<region>.aliyuncs.com) match Alibaba domains.

Alibaba Cloud Text-to-Speech synthesis service.

Configuration

Set the following environment variables:

• ALIYUN_APP_KEY - Application Key
• ALIYUN_ACCESS_KEY_ID - Access Key ID
• ALIYUN_ACCESS_KEY_SECRET - Access Key Secret (sensitive)

Option 1: CLI configuration (recommended)

# Configure App Key
clawdbot skills config aliyun-tts ALIYUN_APP_KEY "your-app-key"

# Configure Access Key ID
clawdbot skills config aliyun-tts ALIYUN_ACCESS_KEY_ID "your-access-key-id"

# Configure Access Key Secret (sensitive)
clawdbot skills config aliyun-tts ALIYUN_ACCESS_KEY_SECRET "your-access-key-secret"

Option 2: Manual configuration

Edit ~/.clawdbot/clawdbot.json:

{
  skills: {
    entries: {
      "aliyun-tts": {
        env: {
          ALIYUN_APP_KEY: "your-app-key",
          ALIYUN_ACCESS_KEY_ID: "your-access-key-id",
          ALIYUN_ACCESS_KEY_SECRET: "your-access-key-secret"
        }
      }
    }
  }
}

Usage

# Basic usage
{baseDir}/bin/aliyun-tts "Hello, this is Aliyun TTS"

# Specify output file
{baseDir}/bin/aliyun-tts -o /tmp/voice.mp3 "Hello"

# Specify voice
{baseDir}/bin/aliyun-tts -v siyue "Use siyue voice"

# Specify format and sample rate
{baseDir}/bin/aliyun-tts -f mp3 -r 16000 "Audio parameters"

Options

Flag	Description	Default
-o, --output	Output file path	tts.mp3
-v, --voice	Voice name	siyue
-f, --format	Audio format	mp3
-r, --sample-rate	Sample rate	16000

Available Voices

Common voices: siyue, xiaoxuan, xiaoyun, etc. See Alibaba Cloud documentation for the full list.

Chat Voice Replies

When a user requests a voice reply:

# Generate audio
{baseDir}/bin/aliyun-tts -o /tmp/voice-reply.mp3 "Your reply content"

# Include in your response:
# MEDIA:/tmp/voice-reply.mp3