A professional-grade command-line interface for Typecast AI that enables multilingual text-to-speech with granular emotion and prosody control.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install typecast
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install typecast using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Cast (Typecast TTS CLI)?
Cast is a sophisticated text-to-speech (TTS) engine integration for the Openclaw Skills ecosystem that brings human-like synthetic voices to the terminal. It leverages the Typecast API to provide high-fidelity audio generation across 37 languages, allowing developers to play audio immediately or export to high-quality wav and mp3 formats.
Built for creators and developers, this skill stands out by offering advanced emotional intelligence. It supports both explicit emotion presets (like happy, sad, or whisper) and smart emotion inference, where the AI analyzes the surrounding context to determine the most natural tone of voice for the given text.
Cast (Typecast TTS CLI) Use Cases
- Automating voiceovers for social media content like TikToks, Reels, and YouTube shorts.
- Integrating high-quality audio feedback into CLI tools and developer workflows.
- Rapidly prototyping audiobooks or podcast segments with diverse character voices.
- Generating localized e-learning content and multilingual announcements.
- Developing realistic voicemail or NPC dialogue for gaming and interactive applications.
How Cast (Typecast TTS CLI) Works
- The user provides text input via direct CLI arguments, piped stdin, or local file reading.
- Cast detects the language and applies the configured voice ID and model settings (ssfm-v30 or ssfm-v21).
- The engine processes emotion parameters, using the smart inference system to analyze previous and subsequent text for better prosody.
- Audio is synthesized via the Typecast API using specified tempo, pitch, and volume adjustments.
- The resulting high-fidelity audio is either streamed directly to the system speakers for immediate playback or saved to a designated output file.
Cast (Typecast TTS CLI) Setup
To integrate this capability into your Openclaw Skills environment, install the cast CLI via Homebrew and configure your API credentials:
# Install the cast CLI
brew tap neosapience/tap
brew install cast
# Authenticate with your Typecast API Key
cast login <your_api_key>
# Set a default voice to get started
cast config set voice-id <voice_id>
Cast (Typecast TTS CLI) Data Schema & Taxonomy
The skill manages configuration and output through a structured hierarchy of priorities: CLI flags, environment variables, and a local configuration file.
| Component | Details |
|---|---|
| Config File | Located at ~/.typecast/config.yaml |
| Audio Formats | Supports .wav (default) and .mp3 |
| Metadata | Tracks reproducibility through a seed parameter |
| Language Support | ISO 639-3 codes (e.g., eng, kor, jpn, fra, vie) |
| Models | ssfm-v30 (37 langs, smart emotions) and ssfm-v21 (27 langs, low latency) |
Cast (Typecast TTS CLI) Advanced Features
- Smart Emotion Inference: Automatically calculates the appropriate emotional tone based on the text context.
- Voice Tournament: A unique interactive mode to select the best voice through head-to-head comparisons.
- Granular Prosody Control: Fine-tune audio output with pitch semitones (-12 to +12) and tempo scaling (0.5 to 2.0).
- Deterministic Synthesis: Use the seed flag to ensure reproducible audio generation across different sessions.
- Pipe Integration: Seamlessly chain with other Openclaw Skills by piping text from URLs or local system logs directly into the voice engine.
SKILL.md
Loading
Related Openclaw Skills
Diff Reference Tool
A zero-dependency reference tool providing offline documentation for diff patterns and workflows within AI coding environments.
POD Fulfill Chain
A professional operations skill designed to automate print-on-demand fulfillment routing, supply chain fallback logic, and production SLA monitoring.
KuCoin Unified API Skill
A specialized skill for executing KuCoin public exchange market operations through a curated OpenAPI interface and the uxc execution engine.
Video Editor (ffmpeg)
A comprehensive suite of video processing operations powered by ffmpeg for automated editing, conversion, and optimization.
Text to Podcast
A specialized tool for converting markdown scripts and text articles into high-quality podcast audio using advanced AI speech synthesis.
Knowledge Internalizer Pro
Knowledge Internalizer Pro is a systematic engine designed to help AI agents deeply learn new domains, build structured knowledge bases, and assess their own mastery levels.
Featured*
