Kokoro TTS

Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to "say" something, requests a voice message, or wants text converted to speech.

Security Scan

The skill is a straightforward local TTS wrapper, but it references an undeclared environment variable and will POST user text to whatever KOKORO_API_URL is set to — review the configured endpoint and provenance before installing.

Purpose & Capability

The skill's name, description, and included script all align with a TTS purpose. However, SKILL.md and the script rely on a KOKORO_API_URL environment variable but the registry metadata lists no required env vars — an inconsistency in declared requirements.

Instruction Scope

Runtime instructions are narrowly scoped to generating speech: set KOKORO_API_URL, run the provided Node.js script, and the script writes an MP3 into ./media and prints a MEDIA: path. The instructions do not request unrelated system files or credentials.

Install Mechanism

No install spec; this is an instruction-only skill with a small included Node.js script. No remote downloads or archive extraction are performed by the skill itself.

Credentials

Although no required env vars are declared in the metadata, the script and SKILL.md use KOKORO_API_URL (defaults to http://localhost:8880/v1/audio/speech). Because the endpoint is configurable, user text will be POSTed to whatever URL is set — if that URL points to an untrusted remote server, sensitive content could be exfiltrated. The metadata should explicitly declare KOKORO_API_URL.

Persistence & Privilege

The skill does not request always:true and will not modify other skills or system-wide configs. It writes media files into the current working directory (media/), which is expected behavior for a TTS tool.

What to consider before installing

This skill appears to do only text→speech via a Kokoro API, but there are two things to check before installing: (1) provenance — the skill's source/homepage is unknown; (2) endpoint configuration — by default it posts to localhost, but if KOKORO_API_URL is set to a remote URL that server will receive the raw text you send. Only set KOKORO_API_URL to a server you trust. Also note the skill writes MP3s to a local media/ folder. Recommend: review the included scripts/tts.js yourself (or run in a sandbox), add KOKORO_API_URL to the skill metadata if you accept it, and avoid sending sensitive content unless you control or trust the configured TTS server.

This skill allows you to generate high-quality AI speech using a local or remote Kokoro-TTS instance.

Configuration

The skill uses the KOKORO_API_URL environment variable to locate the API.

• Default: http://localhost:8880/v1/audio/speech
• To Configure: Add KOKORO_API_URL=http://your-server:port/v1/audio/speech to your .env file or environment.

Usage

To generate speech, run the included Node.js script.

Command

node skills/kokoro-tts/scripts/tts.js "<text>" [voice] [speed]

• text: The text to speak. Wrap in quotes.
• voice: (Optional) The voice ID. Defaults to af_heart.
• speed: (Optional) Speech speed (0.25 to 4.0). Defaults to 1.0.

Example

node skills/kokoro-tts/scripts/tts.js "Hello Ed, this is Theosaurus speaking." af_nova

Output

The script will output a single line starting with MEDIA: followed by the path to the generated MP3 file. OpenClaw will automatically pick this up and send it as an audio attachment.

Example Output: MEDIA: media/tts_1706745000000.mp3

Available Voices

Common choices:

• af_heart (Default, Female, Warm)
• af_nova (Female, Professional)
• am_adam (Male, Deep)
• bf_alice (British Female)

For a full list, see references/voices.md or query the API.