What languages does SaluteSpeech support?

The registry indicates this is Sber's SaluteSpeech API, which primarily supports Russian-language speech recognition and synthesis. Check the official Sber SaluteSpeech documentation for the full list of supported languages and locales.

How do I authenticate with the SaluteSpeech MCP server?

Set the required SALUTE_AUTH_KEY environment variable with your API key before starting the server. This key is used to authenticate all requests to the Sber SaluteSpeech API.

What audio formats can I use for speech recognition?

The registry metadata does not specify supported audio formats. Refer to the Sber SaluteSpeech API documentation or test with common formats like WAV, MP3, and OGG.

Is there a cost to use SaluteSpeech through this MCP server?

Pricing depends on your Sber SaluteSpeech API plan. This MCP server is a client library that forwards requests to Sber's service; costs are determined by Sber's pricing model, not the MCP wrapper.

Can I use this server for real-time speech recognition?

The MCP server provides access to SaluteSpeech's speech recognition and synthesis capabilities, but real-time performance depends on the underlying Sber API. Check Sber's documentation for latency and real-time support details.

MCP ServerSTDIOOfficialv1.0.0

Theyahia Salutespeech MCP Server

Convert speech to text and generate synthetic speech from text using Sber's SaluteSpeech API. For developers building voice-enabled applications who need Russian-language speech recognition and synthesis.

io.github.theYahia/salutespeech-mcp

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

1 required env var

What the Theyahia Salutespeech MCP server does

How models use it and what it is built for.

Connect to Theyahia Salutespeech

Local install — runs as a subprocess.

npx @theyahia/salutespeech-mcp@1.0.0

Environment variables

Configuration this server reads at startup.

SALUTE_AUTH_KEYRequiredSecret
API key for the service

Resources

Where to find authoritative docs and source for Theyahia Salutespeech.

Source repository

Example prompts for Theyahia Salutespeech

Paste any of these into Agent Studio after connecting Theyahia Salutespeech.

Transcribe this audio file using SaluteSpeech speech recognition
Generate speech synthesis from Russian text with SaluteSpeech
What audio formats does SaluteSpeech recognize
Show me how to configure the SALUTE_AUTH_KEY for this MCP server

Theyahia Salutespeech MCP server — FAQ

Common questions about connecting and running Theyahia Salutespeech.

What languages does SaluteSpeech support?
The registry indicates this is Sber's SaluteSpeech API, which primarily supports Russian-language speech recognition and synthesis. Check the official Sber SaluteSpeech documentation for the full list of supported languages and locales.
How do I authenticate with the SaluteSpeech MCP server?
Set the required SALUTE_AUTH_KEY environment variable with your API key before starting the server. This key is used to authenticate all requests to the Sber SaluteSpeech API.
What audio formats can I use for speech recognition?
The registry metadata does not specify supported audio formats. Refer to the Sber SaluteSpeech API documentation or test with common formats like WAV, MP3, and OGG.
Is there a cost to use SaluteSpeech through this MCP server?
Pricing depends on your Sber SaluteSpeech API plan. This MCP server is a client library that forwards requests to Sber's service; costs are determined by Sber's pricing model, not the MCP wrapper.
Can I use this server for real-time speech recognition?
The MCP server provides access to SaluteSpeech's speech recognition and synthesis capabilities, but real-time performance depends on the underlying Sber API. Check Sber's documentation for latency and real-time support details.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 40+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio