A
licenseB
qualityD
maintenanceEnables natural language-driven speech synthesis using Fish Audio's Text-to-Speech API, supporting multiple voices, streaming, and flexible configuration.
2
21 npm
MIT
MCP Fish Server
by AceDataCloud
Related Servers
Alternatives to MCP Fish Server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients such as Claude Desktop, Cursor, and Cline to synthesize speech and singing with natural-language pitch and emotion tags, search and switch character voices and engine models, and transcribe audio through the Fish Audio API.2MIT
- 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.26 npmMIT- AlicenseAqualityBmaintenanceEnables AI agents to generate speech using Gemini TTS models, with tools for text-to-speech, task polling, and pricing checks.4177 npmApache 2.0
TDQS
A3.7/5.0
Scored across 7 tools
Disambiguation5/5
Each tool targets a distinct resource+action: audio generation (fish_generate_audio), model lifecycle (create/get/list), task polling (single vs batch), and a documentation tool. The descriptions explicitly pre-empt the main confusion points, e.g. fish_create_model vs fish_generate_audio and fish_get_task vs fish_get_tasks_batch. An agent can select unambiguously.
Naming Consistency5/5
All seven tools use a uniform fish_<verb>_<noun> snake_case pattern (generate_audio, create_model, get_model, get_task, get_tasks_batch, get_usage_guide, list_models). Verb choices (get/create/list/generate) are used consistently with their intent.
Tool Count5/5
Seven tools is a well-scoped surface for a TTS service: generation, async task polling, and voice model management. No redundant or filler tools; each covers a distinct workflow step.
Completeness3/5
Voices can be created, fetched, and listed, but there is no delete/revoke operation for publicly saved models — a notable lifecycle gap given there is no private option. Task tracking also lacks a way to list outstanding tasks without knowing IDs in advance, forcing agents to remember task_ids.
Maintenance
ActivityActive
ResponsivenessNo recent community issues