stt_health
Check if the dTelecom STT service is running and healthy.
LABSCO SUMMARY
The format requirement is the integration: one shape of WAV is accepted, and the description tells you how to produce it.
Most transcription wrappers accept whatever you hand them and fail somewhere in the middle when the sample rate is wrong. This one names PCM16, 16 kHz, mono up front and ships the conversion line next to the requirement, which turns an opaque failure into a preprocessing step. stt_health and stt_pricing exist so the failures that have nothing to do with your audio are checkable in advance: whether the service is running, and what a minute costs — the pricing call charges nothing to ask.
What it is
A speech-to-text server, exposing 3 tools that transcribe a local WAV file through dTelecom and report the service's pricing and health.
What you get
- Transcription from a path on disk: transcribe_file takes a file path, a language and a minutes argument, so the billable quantity is visible at the call site.
- One accepted input shape, stated exactly: the file must be PCM16, 16 kHz, mono — and the tool description carries the ffmpeg invocation that converts anything else into it.
- Price checked before commitment: stt_pricing returns current pricing and explicitly requires no payment to call.
- A liveness check that is separate from a failed transcription: stt_health reports whether the service is running.
Requirements
A dTelecom private key, supplied as DTELECOM_PRIVATE_KEY, and audio already in PCM16 16 kHz mono WAV at a path the server can read.
Setup effort
One command plus credentials — npm install -g @dtelecom/stt-mcp, then supply credentials
USE CASES
01
Transcribing a recording that is already on disk
Confirm the service is up, then send the WAV in the one accepted format with its language and duration.
02
Checking what a batch of audio will cost before sending it
Read the current pricing, which costs nothing to ask, and size the job against it before any audio leaves the machine.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
stt_pricing
Get current dTelecom STT pricing information. No payment required.
transcribe_file
Transcribe a WAV audio file to text using dTelecom STT. The file must be PCM16, 16kHz, mono. Convert with: ffmpeg -i input.mp3 -ar 16000 -ac 1 -acodec pcm_s16le output.wav
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected.
Requires
- npx on PATH
- DTELECOM_PRIVATE_KEY in your environment
Where it runs
All 3 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 3 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g @dtelecom/stt-mcpMCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"dtelecom-stt": {
"command": "dtelecom-stt-mcp",
"env": {
"DTELECOM_PRIVATE_KEY": "<YOUR_DTELECOM_PRIVATE_KEY>"
}
}
}
}Claude Desktop, Cursor
JSON
{
"mcpServers": {
"dtelecom-stt": {
"command": "npx",
"args": [
"-y",
"@dtelecom/stt-mcp"
],
"env": {
"DTELECOM_PRIVATE_KEY": "<YOUR_DTELECOM_PRIVATE_KEY>"
}
}
}
}
