theYahia/salutespeech-mcp
MCP server for SaluteSpeech — speech recognition and synthesis (Russia)
Platform-specific configuration:
{
"mcpServers": {
"salutespeech-mcp": {
"command": "npx",
"args": [
"-y",
"salutespeech-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
MCP server for Sber SaluteSpeech API — speech recognition (STT) and synthesis (TTS). 5 tools.
[](https://www.npmjs.com/package/@theyahia/salutespeech-mcp) [](https://opensource.org/licenses/MIT)
Part of Russian API MCP (50 servers) by @theYahia.
{
"mcpServers": {
"salutespeech": {
"command": "npx",
"args": ["-y", "@theyahia/salutespeech-mcp"],
"env": { "SALUTESPEECH_API_KEY": "your-base64-key" }
}
}
}claude mcp add salutespeech -e SALUTESPEECH_API_KEY=your-key -- npx -y @theyahia/salutespeech-mcpSALUTESPEECH_API_KEY=your-key npx @theyahia/salutespeech-mcp --http --port=3000
# POST http://localhost:3000/mcp
# GET http://localhost:3000/healthThree options (checked in order):
| Env var | Format | |---------|--------| | SALUTESPEECH_API_KEY | Base64-encoded client_id:client_secret | | SALUTE_AUTH_KEY | Same (legacy alias) | | SALUTE_SPEECH_CLIENT_ID + SALUTE_SPEECH_CLIENT_SECRET | Raw credentials (auto-encoded) |
OAuth tokens (scope SALUTE_SPEECH_PERS) are obtained and refreshed automatically. Get credentials at developers.sber.ru.
| Tool | Description | |------|-------------| | recognize_speech | STT from Base64 audio | | synthesize_speech | TTS, returns Base64 audio | | list_models | List recognition models and synthesis voices | | get_task_status | Check async recognition task status | | recognize_file | STT from a local file path |
skill-transcribe — guided workflow for audio transcriptionskill-synthesize — guided workflow for speech synthesisTranscribe the audio fileLoading reviews...