$ loading_
Convert text into natural-sounding speech audio through an MCP server.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Texttospeech Mcp" MCP server from askskill: Run: claude mcp add --transport http 'io-github-varvararatta-texttospeech-mcp' 'https://texttospeech-mcp.mcpize.run/mcp'
Convert the following product introduction into a Chinese female voiceover with a professional and friendly tone at a moderate pace, and return a playable audio result: 'This smartwatch supports heart rate monitoring, sleep analysis, and all-day battery life.'
A natural-sounding product introduction audio clip suitable for promotion.
Turn the following text into English speech in a podcast narration style with clear pronunciation: 'Artificial intelligence is changing how people work, learn, and create.'
A clear and smooth English narration audio clip for podcasts or content previews.
Convert this notice into a concise and formal Chinese spoken announcement: 'The meeting will start at 3 PM. Please enter the meeting room five minutes early.'
A concise and formal announcement audio clip suitable for office or public playback.
Convert, generate, and process HTML and PDF files through MCP-connected APIs.
Access education services for course lookup, learning support, and teaching information.
Run marketing analysis, campaign planning, and promotion automation tasks.
Connect to a research MCP server for finding, organizing, and analyzing information.
Run security checks, reviews, and automated analysis through an MCP server.
Query country data for research, analysis, and application integration.
Convert text to speech via one interface with local and cloud engines.
Convert text into speech with Google TTS, voices, and style templates.
Run local speech-to-text and text-to-speech with configurable engine switching.
Convert text and speech with voice listing, TTS, and transcription tools.
Clone custom voices for AI assistants and generate playable speech inline.
Build voice profiles from samples, then rewrite or generate text in that voice.