"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

An MCP server for local image, speech, music, and SFX generation that preserves character identity across calls and rejects degenerate outputs. It runs with near-zero GPU idle memory and is designed for DeepSeek Harness agents.

Enables AI agents to generate dynamic game background music by analyzing game scenes with DeepSeek and generating royalty-free tracks via Soundraw, including integration code for Unity and Unreal Engine.

Enables comprehensive analysis of MIDI SMF files including loading, parsing, track analysis, event extraction with filtering, and detailed file summaries. Supports memory management for efficient repeated access to loaded MIDI files.

A server that generates MP3 audio files from text using Kokoro TTS technology with optional S3 upload capabilities.

Enables MCP clients to play a fixed built-in audio track and display native Windows/macOS desktop notifications through stdio.

A self-contained daemon that watches a directory, transcribes anything that lands in it, and presents the results to any AI agent through a standard protocol — no cloud, no subscriptions, no vendor lock-in.

An MCP server that exposes a synthesizer composer's command catalog as tools, enabling Claude to compose, sound-design, and mix in a live browser session.

A text-to-speech MCP server with 48 voices across 9 languages, supporting emotion spans, SFX tags, and multi-speaker dialogue. Deployable via a single npx command with built-in guardrails and swappable backends.

A music MCP server enabling multi-agent collaboration where AI agents jam together in real-time, with 20 tools, conductor mode, and zero dependencies.

Enables music composition and playback using Strudel patterns in the terminal. Supports multi-track editing, effects, rendering to WAV, and AI-assisted composition via genre presets.

Enables agents to co-edit live music sessions, create, remix, publish, export MIDI, and analyze musical structure in the Keyboardia collaborative step sequencer.

Enables AI agents to speak and listen in real-time with interruption handling, using local ML models and hot-swappable adapters.

Hosted text-to-speech MCP server for AI agents with 54 neural voices in 9 languages, including Brazilian Portuguese. Pay-per-use API, no GPU or subscriptions needed.

Plays built-in Windows system sounds or WAV files to notify users when tasks finish or need attention, using the winsound module. Provides a single play_sound tool with presets and customizable file paths, repeats, and intervals.

Local voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud.

Enables MCP-capable assistants to transcribe local audio files or URLs and perform speaker diarization for Spanish and Portuguese audio, with options for speaker count hints, domain prompts, and transcript retrieval in multiple formats.

MCP server for Mixxx DJ software that enables AI agents to control transport, mixing, EQ, loops, hotcues, and effects in real time through MIDI and OSC.

Enables AI assistants to search, play, queue, pause, resume, and skip tracks in a shared music room via stdio MCP tools, while a synchronized PWA mini/full player serves human listeners.

Enables playing and inspecting local audio files in an MCP host with an in-conversation UI showing waveform, spectrogram, and loudness metrics, while exposing playback state and metadata to the model.

Two-mode creative music studio for AI: scored composition (ABC notation with sheet music) and live performance (Strudel live coding with TidalCycles), with interactive UI rendering inline in Claude Desktop and other MCP clients.