Yandex Speechkit Mcp

io.github.theYahiaPublished by GitHub account theYahiav1.0.0Updated Oct 24, 2026

MCP server for Yandex SpeechKit API — speech recognition and synthesis.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

MCP server for Yandex SpeechKit that lets an assistant transcribe audio to text, synthesize speech from text, and list available voices.

What you can do
  • Transcribe audio: convert Base64 audio to text with speech recognition, or use a higher-level transcription tool that returns clean text.
  • Synthesize speech: turn text into Base64 audio, or use a higher-level synthesis tool with smart defaults that detects language from the chosen voice.
  • Browse voices: list available text-to-speech voices and filter them by language.
When to use it
Useful when you want an assistant to transcribe audio files or generate spoken audio through Yandex SpeechKit, especially for Russian-language content or when working inside the Yandex Cloud ecosystem.
Requirements
Runs locally via npx from the npm package, or as a Streamable HTTP server on port 8080. Needs a Yandex Cloud API key (YANDEX_SPEECHKIT_API_KEY, with YANDEX_API_KEY as a legacy alias, or an IAM_TOKEN) and a Yandex Cloud folder ID (FOLDER_ID). Network access to Yandex Cloud is required.
Before you install
Requires a Yandex Cloud API key or IAM token and folder ID as environment variables; keep them out of shared configs. Audio and text are sent to Yandex SpeechKit, a third party, and usage may be billed by Yandex Cloud. The repository is archived and development has moved to another repository, so the npm package may not receive updates here.

Installation

In SourceWeft

  1. Open Yandex Speechkit Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

🗄 Репозиторий заархивирован

Разработка переехала в theYahia/YaAll — сборку, где весь яндексовский слой лежит в одном месте: свои MCP-серверы, скиллы Claude Code и материалы официальных наборов Яндекса.

Актуальная версия того, что лежало здесь: mcp/yandex-speechkit-mcp/

Пакет в npm прежний — @theyahia/yandex-speechkit-mcp, ставится и работает как раньше. Здесь больше ничего не обновляется. Задачи и pull request'ы — в YaAll.

Archived — development moved to theYahia/YaAll, a single repository bundling the whole Yandex stack. The current version of this package now lives at mcp/yandex-speechkit-mcp/. The npm package @theyahia/yandex-speechkit-mcp is unchanged. Please open issues and pull requests there.

Этот сервер входит в сборку theYahia/YaAll — весь яндексовский слой в одном репозитории: десять MCP-серверов, скиллы Claude Code под SEO и валидацию спроса, плюс материалы официальных серверов Яндекса. Здесь он живёт отдельно, там — рядом с остальными: mcp/yandex-speechkit-mcp/

Part of theYahia/YaAll — the whole Yandex stack in one repo.

@theyahia/yandex-speechkit-mcp

MCP server for Yandex SpeechKit API — speech recognition, synthesis, and voice listing. 5 tools.

[npm] [License: MIT]

Part of the Russian API MCP series by @theYahia.

Installation

Claude Desktop

json
{  "mcpServers": {    "yandex-speechkit": {      "command": "npx",      "args": ["-y", "@theyahia/yandex-speechkit-mcp"],      "env": {        "YANDEX_SPEECHKIT_API_KEY": "your-api-key",        "FOLDER_ID": "your-folder-id"      }    }  }}

Claude Code

bash
claude mcp add yandex-speechkit \  -e YANDEX_SPEECHKIT_API_KEY=your-api-key \  -e FOLDER_ID=your-folder-id \  -- npx -y @theyahia/yandex-speechkit-mcp

Streamable HTTP (remote / Docker)

bash
YANDEX_SPEECHKIT_API_KEY=... FOLDER_ID=... npx @theyahia/yandex-speechkit-mcp --http# Listens on :8080/mcp (override with PORT env var)

Smithery

Deploy via smithery.ai — config in smithery.yaml.

Authentication

VariableDescription
YANDEX_SPEECHKIT_API_KEYYandex Cloud API key (preferred)
YANDEX_API_KEYLegacy alias (still works)
IAM_TOKENShort-lived IAM token (alternative to API key)
FOLDER_IDYandex Cloud folder ID (required)
YANDEX_FOLDER_IDLegacy alias for FOLDER_ID

Get credentials at Yandex Cloud Console.

Tools (5)

ToolTypeDescription
recognizeCoreSpeech recognition (STT) — Base64 audio to text
synthesizeCoreSpeech synthesis (TTS) — text to Base64 audio
list_voicesCoreList available TTS voices, filter by language
skill_transcribeSkillHigh-level transcription — returns clean text
skill_synthesizeSkillHigh-level synthesis — smart defaults, auto-detects language from voice

Examples

Transcribe this audio fileSynthesize "Hello, how are you?" with voice filippWhat voices are available in Russian?Speak this text using the alena voice

Development

bash
npm installnpm run buildnpm testnpm run dev    # stdio mode

License

MIT

Source: README.md at commit c5bce85

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts