"MCP servers that use streamable HTTP as transport" matching MCP servers:

Enables control of Spotify through natural language by searching the catalog, managing playback and devices, controlling playlists, and managing saved songs. Includes OAuth authentication and streamable HTTP transport for remote connectivity.

Provides MCP servers for ElevenLabs (text-to-speech and sound effects) and Meshy.ai (3D generation), with a request preview mode to inspect API calls without incurring costs.

A set of MCP servers that compile, render, or play Faust DSP code, enabling offline analysis, real-time playback, and browser-based audio processing.

MCP server that provides a transcribe_audio tool to convert voice messages from channels into text using OpenAI Whisper, enabling Claude Code to process audio attachments.

Generate music with Suno (v5.5) from any MCP client — async, and billed only on successful renders (a failed render auto-refunds). Hosted Streamable-HTTP server; tools generate_song / wait_for_song / check_song.

Official MCP server for Rendobar. Lets AI agents run serverless media processing and upload local files.

An MCP server that converts short text summaries into spoken audio and plays them locally, designed for coding agents like Claude Code to announce task results.

MCP server for Astra's Companion API v2 that lets Claude and other MCP clients view and control a running Astra desktop music player, including playback, search, queue, favorites, and playlists.

MCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.

Enables AI assistants to transcribe audio files using dTelecom's real-time speech-to-text with pay-per-use USDC micropayments, no API keys required.

MCP server for SpeechWeave transcription, enabling AI assistants to transcribe local files and URLs via wait-first or async tools.

A modular suite of MCP servers for Audiokinetic Wwise, enabling AI agents to browse, edit, audition, profile, and build Wwise projects through the Wwise Authoring API.

Provides on-device Chinese speech recognition with traditional Chinese (Taiwan) output via MCP server, HTTP API, and CLI, ensuring privacy by processing audio locally without uploading to cloud services.

A Model Context Protocol implementation that plays sound effects (completion, error, notification) for Cursor AI and other MCP-compatible environments, providing audio feedback for a more interactive coding experience.

Generates room impulse responses as WAV files from natural language descriptions, enabling agents to create realistic or arbitrary reverb for audio production.

This MCP server enables audio transcription using OpenAI Whisper, supporting various model sizes and base64-encoded audio input via stdio or HTTP transport.

MCP server for generating retro game sound effects using Bfxr synthesis. It provides tools to create, mutate, and load sound parameters, with output saved as WAV files and optional permalinks.

An MCP server that lets users generate, edit, and save Xfer Serum 2 presets from plain-English descriptions directly through MCP clients like Claude Code or Claude Desktop, without any separate API keys or LLM calls.

Render, analyze, and verify audio (WAV or FLAC) through a fully offline, deterministic engine, exposed as MCP tools for AI agents.

An MCP server that masters audio with a professional signal chain using ffmpeg, enabling loudness analysis, vocal-over-beat mixing, full mastering to target LUFS, and Dolby codec export.