gemini-tts-mcp
Related Servers
Alternatives to gemini-tts-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables text-to-speech generation with emoji vocal cues like whispers, sighs and kisses, plus multi-voice scenes where each segment uses its own voice and language across 29 voices and 22 languages, secured by OAuth 2.1.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to generate speech using Gemini TTS models, with tools for text-to-speech, task polling, and pricing checks.4169 npmApache 2.0
- AlicenseAqualityCmaintenanceEnables text-to-speech synthesis through a streaming, GPU-accelerated gateway, exposing a single tool that returns playable WAV audio with configurable voice and speed.133 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables text-to-speech generation using ten built-in voices and saves the resulting audio as a local WAV file.MIT

audio.ditto/ttsofficial
FlicenseNot gradedqualityCmaintenanceEnables AI clients to browse voices and languages and synthesize text into downloadable audio links, including batch jobs of up to 1,000 texts.1-- FlicenseNot gradedqualityDmaintenanceEnables image generation using Google Gemini models (flash/pro) with support for multiple sizes, reference images, and access control via Google OAuth and email allow-lists.1-
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes: generation, planning, voice creation/deletion, listing, and auth handling. There is minor overlap between list_models and list_voices regarding prebuilt voices, and design_voice vs plan_speech both reason about voice selection, but the descriptions make the boundaries reasonably clear.
Six of eight tools follow a clean verb_noun pattern (list_models, list_voices, design_voice, plan_speech, generate_speech, delete_voice). The auth-related tools reauthorize and auth_status deviate slightly, but the overall convention is still predictable.
Eight tools is well-scoped for a TTS MCP server covering auth, discovery, voice design, planning, generation, and cleanup. Each tool appears to earn its place without obvious redundancy.
The surface covers the core lifecycle: auth status/reauthorization, model and voice discovery, voice creation, speech planning, speech generation, and voice deletion. Minor gaps exist, such as no direct voice rename/update operation or generated-audio history, but these are workable around by redesigning voices or managing files externally.