
Connects Claude to Yandex SpeechKit for Russian and multilingual speech operations. You get five tools: recognize and synthesize for direct STT/TTS with base64 audio, list_voices to browse available speakers with language filters, plus two convenience wrappers (skill_transcribe and skill_synthesize) that handle common cases with smart defaults. Requires a Yandex Cloud API key and folder ID. The skill tools auto-detect language from voice selection and return clean output without extra ceremony. Part of a broader Russian API MCP series. Useful if you're building voice interfaces or need programmatic access to Yandex's speech models without leaving your Claude workflow.
🗄 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-mcpis 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.
MCP server for Yandex SpeechKit API — speech recognition, synthesis, and voice listing. 5 tools.
Part of the Russian API MCP series by @theYahia.
{
"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 mcp add yandex-speechkit \
-e YANDEX_SPEECHKIT_API_KEY=your-api-key \
-e FOLDER_ID=your-folder-id \
-- npx -y @theyahia/yandex-speechkit-mcp
YANDEX_SPEECHKIT_API_KEY=... FOLDER_ID=... npx @theyahia/yandex-speechkit-mcp --http
# Listens on :8080/mcp (override with PORT env var)
Deploy via smithery.ai — config in smithery.yaml.
| Variable | Description |
|---|---|
YANDEX_SPEECHKIT_API_KEY | Yandex Cloud API key (preferred) |
YANDEX_API_KEY | Legacy alias (still works) |
IAM_TOKEN | Short-lived IAM token (alternative to API key) |
FOLDER_ID | Yandex Cloud folder ID (required) |
YANDEX_FOLDER_ID | Legacy alias for FOLDER_ID |
Get credentials at Yandex Cloud Console.
| Tool | Type | Description |
|---|---|---|
recognize | Core | Speech recognition (STT) — Base64 audio to text |
synthesize | Core | Speech synthesis (TTS) — text to Base64 audio |
list_voices | Core | List available TTS voices, filter by language |
skill_transcribe | Skill | High-level transcription — returns clean text |
skill_synthesize | Skill | High-level synthesis — smart defaults, auto-detects language from voice |
Transcribe this audio file
Synthesize "Hello, how are you?" with voice filipp
What voices are available in Russian?
Speak this text using the alena voice
npm install
npm run build
npm test
npm run dev # stdio mode
MIT
YANDEX_API_KEY*secretAPI key for the service