voicememos-mcp
by vsalmens
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SONIOX_BASE_URL | No | Soniox EU endpoint, e.g. `https://api.eu.soniox.com` | |
| VOICEMEMOS_SINCE | No | only auto-transcribe memos from this date on | |
| VOICEMEMOS_WORKER | No | With the default `VOICEMEMOS_WORKER=launchd`, the MCP server has no secrets and no access to Voice Memos; it can only queue requests. In `inprocess` mode it does both itself. | launchd |
| VOICEMEMOS_MARKERS | No | spoken words that tag a sentence; `*` accepts inflected forms (`question*=Question`) | idea=Idea,task=Task,... |
| VOICEMEMOS_LANGUAGES | No | language hints, e.g. `fi,en` | en |
| VOICEMEMOS_MARKER_END | No | end word after the wake word that closes a longer marker, e.g. `end` | |
| VOICEMEMOS_OUTPUT_DIR | No | outside Documents on purpose, see [Where transcripts live](#where-transcripts-live) | ~/Library/Application Support/voicememos-mcp/transcripts |
| VOICEMEMOS_DIARIZATION | No | separate speakers in conversations | 1 |
| VOICEMEMOS_MARKER_WAKE | No | wake word required before a marker word, e.g. `dictate*`; empty = marker word alone | |
| VOICEMEMOS_MAX_ATTEMPTS | No | failed after this many tries | |
| VOICEMEMOS_ROAM_ENABLED | No | append new transcripts to Roam daily notes | 0 |
| VOICEMEMOS_CONTEXT_TERMS | No | names and rare terms the engine should know | |
| VOICEMEMOS_SECOND_READER | No | `gemini` = second reading for every new memo, `gemini-low` = only for memos with low certainty | |
| VOICEMEMOS_CONF_THRESHOLD | No | words below this are marked | 0.70 |
| VOICEMEMOS_EXCLUDE_FOLDERS | No | Voice Memos folders hidden from everything | |
| VOICEMEMOS_VOICEPRINT_NAME | No | your name, shown when the voiceprint recognises you | |
| VOICEMEMOS_VOICEPRINT_MODEL | No | accepts `wespeaker_en_voxceleb_resnet34_LM` | |
| VOICEMEMOS_TIMESTAMP_EVERY_S | No | time in the recording at the start of a paragraph, at most once a minute | |
| VOICEMEMOS_EXCLUDE_TITLE_REGEX | No | titles hidden from everything | |
| VOICEMEMOS_SECOND_READER_MODEL | No | gemini-4-argon | |
| VOICEMEMOS_SECOND_READER_MAX_MIN | No | longer recordings are read in parts | 60 |
| VOICEMEMOS_SECOND_READER_CHUNK_MIN | No | approximate length of a part | 30 |
| VOICEMEMOS_SECOND_READER_MIN_AGREEMENT | No | A reading that agrees with the primary words on less than a tenth of the words is rejected | 0.1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues