菜单
Google Speech — transcribe audio to text (speech-to-text) and convert text to speech (TTS). Supports multiple languages and audio formats via `robomotion googlespeech`. Do NOT use for OpenAI Whisper, ElevenLabs, or other speech services.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems, flow fields, shaders (GLSL), pixel manipulation, kinetic typography, WebGL scenes, audio analysis, mouse/keyboard interaction, and headless high-res export. Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
Airtable database client — manage records, tables, and bases in Airtable. Supports CRUD operations, formula-based search, bulk operations, and comments via `robomotion airtable`. Do NOT use for Google Sheets, Excel, Baserow, NocoDB, or other spreadsheet/database tools.
Apify web scraping platform — run Apify actors for large-scale crawling and data extraction. Supports actor execution, run monitoring, and dataset retrieval via `robomotion apify`. Do NOT use for simple HTML parsing or non-Apify scraping tools.
Apollo.io sales intelligence — search 265M+ contacts, enrich leads, manage contacts/accounts/deals. Supports people search, organization enrichment, and CRM operations via `robomotion apollo`. Do NOT use for HubSpot, Salesforce, or other CRM systems.
Baserow open-source database — manage rows, tables, and fields in self-hosted or cloud Baserow instances. Supports CRUD, filtering, sorting, search, and field listing via `robomotion baserow`. Do NOT use for Airtable, NocoDB, Google Sheets, or other no-code databases.
Binance cryptocurrency exchange — trade crypto, check prices, view balances, and access market data. Supports limit/market/stop orders, price history, deposits, and withdrawals via `robomotion binance`. Do NOT use for Gate.io, Coinbase, or other crypto exchanges.
| name | google-speech |
| description | Google Speech — transcribe audio to text (speech-to-text) and convert text to speech (TTS). Supports multiple languages and audio formats via `robomotion googlespeech`. Do NOT use for OpenAI Whisper, ElevenLabs, or other speech services. |
| version | 1.0.0 |
| author | robomotion |
| license | Apache-2.0 |
| tags | ["google","speech","transcription","tts","stt","ai"] |
The robomotion googlespeech CLI connects to Google Cloud Speech APIs for audio transcription and speech synthesis. It transcribes audio files to text and converts text to speech audio files.
robomotion CLI installedrobomotion install googlespeechEach CLI command runs as a separate process — connection IDs from connect do NOT persist across calls.
You MUST use --session on connect and pass --session-id to all subsequent commands.
robomotion install googlespeechrobomotion googlespeech connect --session --output json
# → {"outClientId":"<client-id>","session_id":"<session-id>"}
client-id and session-id in all subsequent commands:
robomotion googlespeech speech_to_text --client-id "<client-id>" --audio-file <path> --session-id "<session-id>" --output json
robomotion googlespeech disconnect --client-id "<client-id>" --session-id "<session-id>" --output json
Always append --output json to get structured JSON results.
robomotion googlespeech speech_to_text --gcs-uri [--sample-rate] [--language-code] [--model] --output json
Convert speech audio from Google Cloud Storage to text using Google Cloud Speech-to-Text APIrobomotion googlespeech text_to_speech --text --input-path [--audio-encoding] [--language-code] [--voice-name] [--sample-rate] --output json
Convert text to speech audio using Google Cloud Text-to-Speech API