Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MISTRAL_API_KEYYesYour Mistral API key for transcription.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
mistral_set_workdirA

Set the work directory for transcription. Creates inbox/ and .staging/ subdirectories if needed.

mistral_get_workdirA

Show current work directory path and status.

mistral_set_context_biasA

Set context bias terms for better transcription accuracy.

Accepts comma-separated or newline-separated terms (max 100). If 'terms' is a file path relative to the work directory, reads terms from that file.

mistral_get_context_biasA

Show currently configured context bias terms.

mistral_clear_context_biasA

Clear all context bias terms.

mistral_set_languageA

Set the transcription language.

Default is English with timestamps enabled. Setting a non-English language automatically disables timestamps (Mistral API constraint: language and timestamp_granularities are mutually exclusive).

mistral_get_languageA

Show current transcription language and whether timestamps are active.

mistral_list_inboxA

List audio files in inbox/ waiting to be transcribed.

mistral_create_sessionA

Create a staging session from audio files in inbox/.

Copies the specified files (or all inbox files) into a staging session for transcription.

mistral_list_sessionsA

List active staging sessions.

mistral_read_staging_transcriptA

Read the merged transcript from a staging session.

Use this to review the transcript before finalizing with a name.

mistral_transcribeA

Transcribe all audio files in a staging session.

Uses the session language set via mistral_set_language (default: English).

mistral_finalizeA

Finalize a staging session into a named recording directory.

Creates a directory under workdir with the given name (slugified), moves audio files into it, writes the merged transcript.md, and cleans up the staging session and inbox originals.

mistral_list_recordingsA

List finalized recording directories.

mistral_read_transcriptA

Read a transcript from a finalized recording.

mistral_save_processedA

Save a cleaned transcript into a finalized recording directory.

Writes the content as transcript_clean.md.

Prompts

Interactive templates invoked by user choice

NameDescription
clean_transcriptClean a raw transcript: remove filler words, fix grammar and logic flow, restructure for clarity while preserving meaning and speaker headings. After the LLM produces the cleaned text, save it with mistral_save_processed.

Resources

Contextual data attached and managed by the client

NameDescription
supported_formatsSupported audio formats, limits, and model information.

Latest Blog Posts

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/HiteSit/voxtract'

If you have feedback or need assistance with the MCP directory API, please join our Discord server