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.
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
io.github.socialapishub/social-media-api
io.github.xpaysh/social-media
com.thenextgennexus/youtube-media-mcp-server
io.github.ludmila-omlopes/youtube-video-analyzer
csoai-org/social-media-ai-mcp
com.ezbizservices/social-media