A cross-platform command-line tool for professional speech-to-text transcription powered by multiple leading AI providers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install speechall-cli
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 speechall-cli 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 speechall-cli?
The speechall-cli is a robust interface for the Speechall API, allowing developers to process audio and video files directly from the command line. This utility is a vital component for those building automated workflows within Openclaw Skills, providing access to top-tier models from OpenAI, Deepgram, Google, and more. It simplifies the transition from raw media to structured text, supporting various output formats like SRT and VTT for immediate use in production environments.
By incorporating this tool into your Openclaw Skills environment, you gain the ability to handle complex transcription tasks including speaker diarization and custom vocabulary boosting. Whether you are processing a single interview or thousands of calls, this CLI provides the speed and flexibility required for modern AI-driven development.
speechall-cli Use Cases
- Rapid transcription of meeting recordings and interviews directly from the terminal.
- Automated generation of SRT or VTT subtitle files for video content within Openclaw Skills pipelines.
- Large-scale processing of audio datasets for data analysis or machine learning training.
- Integration into shell scripts to trigger speech-to-text events automatically.
- Comparing model accuracy across different providers like Deepgram, AssemblyAI, and OpenAI.
How speechall-cli Works
- The user installs the CLI via Homebrew or by downloading the binary to their system path.
- An API key is configured as an environment variable to authenticate with the Speechall service.
- The user executes the speechall command followed by the media file path and optional configuration flags.
- The tool uploads the media (extracting audio automatically on macOS) and processes it using the specified AI model.
- The resulting transcription is output to the terminal or redirected to a local file for further use in Openclaw Skills.
speechall-cli Setup
To begin using this tool with your Openclaw Skills setup, install it via Homebrew:
brew install Speechall/tap/speechall
Next, authenticate by exporting your API key (generate one at speechall.com/console/api-keys):
export SPEECHALL_API_KEY="your-key-here"
Verify the installation:
speechall --version
speechall-cli Data Schema & Taxonomy
The skill manages data primarily through output redirection and specific format flags. When used with Openclaw Skills, it generates structured data as follows:
| Data Type | Format | Description |
|---|---|---|
| Transcription | .txt, .json | Standard text or detailed JSON containing timestamps. |
| Subtitles | .srt, .vtt | Timed text files for video accessibility. |
| Model Metadata | JSON | Detailed list of capabilities for each supported STT provider. |
| Speaker Labels | String Tags | Identifies different speakers when --diarization is enabled. |
speechall-cli Advanced Features
- Speaker Diarization: Automatically distinguish between multiple participants in a conversation to enhance your Openclaw Skills data output.
- Custom Vocabulary: Improve recognition of industry-specific jargon or technical terms by passing custom terms to the model.
- Multi-Provider Model Filtering: Use the models command to find specific capabilities like real-time streaming or specific language support.
- Video-to-Audio Extraction: Native macOS support for extracting audio tracks from video containers before processing.
- Ruleset Integration: Apply custom replacement rules via UUID to sanitize or format output automatically within Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
record CLI
A powerful macOS command-line utility for capturing audio, screen recordings, screenshots, and camera input, optimized for terminal-based AI agents.
Skill Search
A multi-modal search engine for AI agents to discover, match, and load specialized capabilities through keyword, semantic, or LLM-powered matching.
Smart Intent Router Skill
An intelligent model dispatching system that uses multi-dimensional analysis to route requests to the most efficient AI model based on complexity and cost.
OpenClaw Reference Manual
A complete technical reference for managing OpenClaw configurations, CLI operations, and multi-channel AI agent deployments.
Translate CLI
A robust command-line interface for translating text, files, and code catalogs using various AI providers and custom prompt templates.
MCP Atlassian Server
A Docker-based Model Context Protocol server that bridges AI agents with Atlassian tools like Jira and Confluence for automated project management.
Featured*
