salutespeech-mcp
This server integrates Sber's SaluteSpeech API, providing speech recognition (STT) and synthesis (TTS) capabilities via 5 tools:
recognize_speech: Transcribe audio from Base64-encoded data, supporting Russian (ru-RU), English (en-US), and Kazakh (kk-KZ), with a 2MB/1-minute audio limit and multiple formats (WAV, OGG/Opus, MP3).recognize_file: Transcribe audio from a local file path, with automatic format detection from the file extension, subject to the same 2MB/1-minute limit.synthesize_speech: Convert text (up to 4,000 characters) to speech, returning Base64-encoded audio. Supports multiple voices (e.g., Nec_24000, Bys_24000) and output formats (opus, wav16, pcm16).list_models: List available recognition models and synthesis voices, with optional filtering by type (recognition, synthesis, or all).get_task_status: Check the status of an asynchronous recognition task using its task ID.
Authentication is supported via SALUTESPEECH_API_KEY (base64-encoded client_id:client_secret), SALUTE_AUTH_KEY (legacy alias), or separate SALUTE_SPEECH_CLIENT_ID and SALUTE_SPEECH_CLIENT_SECRET environment variables.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@salutespeech-mcpTranscribe the audio file recording.wav"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@theyahia/salutespeech-mcp
MCP server for Sber SaluteSpeech API — speech recognition (STT) and synthesis (TTS). 5 tools.
Part of Russian API MCP (50 servers) by @theYahia.
Install
Claude Desktop
{
"mcpServers": {
"salutespeech": {
"command": "npx",
"args": ["-y", "@theyahia/salutespeech-mcp"],
"env": { "SALUTESPEECH_API_KEY": "your-base64-key" }
}
}
}Claude Code
claude mcp add salutespeech -e SALUTESPEECH_API_KEY=your-key -- npx -y @theyahia/salutespeech-mcpStreamable HTTP mode
SALUTESPEECH_API_KEY=your-key npx @theyahia/salutespeech-mcp --http --port=3000
# POST http://localhost:3000/mcp
# GET http://localhost:3000/healthRelated MCP server: @theyahia/yandex-speechkit-mcp
Auth
Three options (checked in order):
Env var | Format |
| Base64-encoded |
| Same (legacy alias) |
| Raw credentials (auto-encoded) |
OAuth tokens are obtained and refreshed automatically. The scope defaults to
SALUTE_SPEECH_PERS (individuals); set SALUTE_SPEECH_SCOPE for corporate accounts
(SALUTE_SPEECH_CORP — postpaid, SALUTE_SPEECH_B2B — prepaid).
Get credentials at developers.sber.ru.
Tools (5)
Tool | Description |
| STT from Base64 audio |
| TTS, returns Base64 audio |
| List recognition models and synthesis voices |
| Check async recognition task status |
| STT from a local file path |
Skills
skill-transcribe— guided workflow for audio transcriptionskill-synthesize— guided workflow for speech synthesis
Examples
Transcribe the audio file /tmp/meeting.wav
Synthesize "Hello world" with voice Bys_24000 in wav16 format
List available voicesLimits
recognize_speech / recognize_file use the synchronous endpoint, capped at
2 MB / 1 minute of audio (larger input returns HTTP 413). For multi-channel audio only
the first channel is recognized. Longer recordings need the asynchronous flow
(data:upload → speech:async_recognize → task:get → data:download) — not yet exposed
as tools; get_task_status covers the polling step.
Synthesis input is capped at 4000 characters (incl. spaces and SSML markup).
Troubleshooting
self-signed certificate in certificate chain / UNABLE_TO_VERIFY_LEAF_SIGNATURE
Sber's endpoints use the Russian Trusted Root CA (НУЦ Минцифры), which is not in Node.js's default trust store — so the very first OAuth call fails until you trust it.
Fix: download the root CA (russian_trusted_root_ca_pem.crt) from
gosuslugi.ru/crt and point Node at it:
export NODE_EXTRA_CA_CERTS=/path/to/russian_trusted_root_ca_pem.crtIn an MCP client, add it to the server's env block. Do not set
NODE_TLS_REJECT_UNAUTHORIZED=0 in production — it disables TLS verification entirely.
Official guide: SaluteSpeech certificates.
License
MIT
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/theYahia/salutespeech-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server