MCP Fish Server
Related Servers
Alternatives to MCP Fish Server
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceEnables natural language-driven speech synthesis using Fish Audio's Text-to-Speech API, supporting multiple voices, streaming, and flexible configuration.229 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides text-to-speech functionality using OpenAI's TTS API, enabling text-to-speech conversion, voice listing, and model listing.MIT
- AlicenseAqualityFmaintenanceEnables text-to-speech conversion using ElevenLabs API with voice management, streaming support, and multiple models.51MIT

leanvox-mcpofficial
AlicenseNot gradedqualityDmaintenanceEnables text-to-speech generation, voice cloning, dialogue creation, and other TTS operations through natural language in MCP-compatible AI assistants.12 npmMIT- AlicenseAqualityBmaintenanceEnables AI agents to generate speech using Gemini TTS models, with tools for text-to-speech, task polling, and pricing checks.463 npmApache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables voice cloning and speech synthesis through Alibaba Cloud's Bailian and DashScope platforms. It provides tools to create, manage, and synthesize audio using custom cloned voice profiles.-
TDQS
Scored across 6 tools
Each tool has a clear, distinct role: generating audio, retrieving individual models, listing models, checking single or batch task status, and providing usage guidance. There is no meaningful overlap between any of the tools.
All tools follow a consistent fish_ prefix with a clear verb_noun pattern: generate_audio, get_model, get_task, get_tasks_batch, get_usage_guide, list_models. The naming is predictable and easy to navigate.
Six tools is an appropriate, well-scoped count for a TTS-focused server. Each tool serves a necessary function without redundancy or bloat.
The surface covers the core generation workflow: create a task, poll its status, check batches, and browse voice models. Minor gaps like canceling a task or listing all tasks without IDs are absent, but the main workflow is fully supported.