# Voice Coach (pypi · voice-coach-mcp)

Gives Claude ears: local pitch, pronunciation and public-speaking analysis for voice coaching.

- Trust score: 63/100 (medium)
- Change this week: −15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `voice-coach-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp.md), [page](https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp)

## Channel facts

- Registry: `pypi`
- Package: `voice-coach-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 59 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to FabianIMV/voice-coach-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1478 tokens (~211/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Voice Coach MCP server?

Voice Coach runs locally as a PyPI package, launched with uvx voice-coach-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add fabianimv-voice-coach-mcp -- uvx voice-coach-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "fabianimv-voice-coach-mcp": {
      "command": "uvx",
      "args": [
        "voice-coach-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fabianimv-voice-coach-mcp": {
      "command": "uvx",
      "args": [
        "voice-coach-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add fabianimv-voice-coach-mcp -- uvx voice-coach-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fabianimv-voice-coach-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "voice-coach-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fabianimv-voice-coach-mcp --command uvx --arg voice-coach-mcp
```

### Hermes

```yaml
mcp_servers:
  fabianimv-voice-coach-mcp:
    command: "uvx"
    args: ["voice-coach-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "fabianimv-voice-coach-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "voice-coach-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add fabianimv-voice-coach-mcp -t stdio -c uvx -a voice-coach-mcp
```

### Other

```json
{
  "mcpServers": {
    "fabianimv-voice-coach-mcp": {
      "command": "uvx",
      "args": [
        "voice-coach-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-04 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-29 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-25 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-24 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (7)

### `record_audio` (~137 tokens)

Records from the computer's microphone and saves a 16 kHz mono .wav.

Args:
    seconds: recording length (max 120 by default). Tell the user before calling.
    name: optional file name (without extension); defaults to date and time.

Returns `audio` (path of the .wav), levels (peak/RMS in dBFS, estimated SNR, % clipping),
\`confidence` and `warnings`. The `no_microphone_permission` warning means macOS delivered no
audio: the user must enable the microphone for the app in System Settings.

Input parameters:

- `name`
- `seconds` (number, required)

Output parameters:

- `result` (string)

### `analyze_pitch` (~387 tokens)

Measures the pitch accuracy of sung audio (solo voice, one melodic line).

Args:
    audio: audio path (wav/flac/mp3/m4a) or a name returned by record_audio.
    reference_midi: optional path to a .mid with the expected melody. Tolerates singing an
        octave up/down, starting at another moment and a somewhat different tempo.
    key: optional when there is no MIDI, e.g. "A minor", "G major", "F#" (Spanish names such as
        "La menor" also work): each note is compared with the nearest note of that scale.
        Without it, with the nearest equal-tempered note.
    midi_track: index of the MIDI track to use (default: the non-drum track with most notes).

Returns `summary` (notes, range, pct_within_25_cents, signed mean_deviation_cents,
tendency flat/sharp/centered, drift_cents between 1st and 2nd half, stability counts; with
MIDI also missed, extra_notes, wrong_notes, onsets on_time/late/early, octave_shift,
start_offset_ms and relative_tempo >1 = slower) and `notes`: t (s), dur, note or
expected/sung, cents (+ = sharp), stability (stable | vibrato with vibrato_hz and
vibrato_pp_cents | unstable with std_cents), drift_cents within the note and, with MIDI,
onset_ms/onset; reference notes not sung have status=missed and unmatched sung notes
status=extra. If the list does not fit, the most problematic notes are shown and the rest
is in `full_details`.

Input parameters:

- `audio` (string, required)
- `key`
- `midi_track`
- `reference_midi`

Output parameters:

- `result` (string)

### `transcribe` (~143 tokens)

Transcribes audio with timestamps (faster-whisper, local).

Args:
    audio: audio path or a name returned by record_audio.
    language: "en", "es", "en-US", "Spanish"…; auto-detected when omitted.

Returns `language`, `language_prob`, `text`, `segments` [{t, end, text}] and `words`
[{w, t, end}]. If it does not fit, words are dropped first and then segments (everything
stays in `full_details`). The first call downloads the model (VOICE_COACH_WHISPER_MODEL).

Input parameters:

- `audio` (string, required)
- `language`

Output parameters:

- `result` (string)

### `speech_metrics` (~293 tokens)

Measures pace, pauses, filler words and pitch/volume variation of a speech.

Args:
    audio: audio path or a name returned by record_audio.
    language: language of the speech ("en" or "es"; filler lists exist for both).
    pause_threshold_s: minimum silence between words to count as a long pause.

Returns:
\- `pace`: words, speaking_time_s, words_per_minute, wpm_excluding_long_pauses.
\- `pauses`: count, total_s, max_s, per_minute and items [{t, dur, after: previous word}].
\- `fillers`: total, per_minute, by_type and occurrences [{t, text}]. Ambiguous words
  ("like", "so") only count when isolated by a comma or a pause.
\- `pitch`: median_f0_hz, std_semitones, range_p10_p90_semitones, monotone (std < 2 st) and
  monotone_stretches [{t, end}] over 8 s windows.
\- `volume`: mean_dbfs, std_between_words_db, range_p10_p90_db, low_variation (std < 3 dB).
\- `segments` of the transcript [{t, end, text}].

Input parameters:

- `audio` (string, required)
- `language` (string, required)
- `pause_threshold_s` (number)

Output parameters:

- `result` (string)

### `assess_pronunciation` (~289 tokens)

Compares the pronounced phonemes with the expected ones for a text read aloud (English).

Args:
    audio: audio path or a name returned by record_audio (up to 60 s; short sentences work best).
    expected_text: the exact text that was read.
    language: "en-US" (default) or "en-GB".

Returns `summary` (overall_score 0–100, words_with_errors, error counts by type,
frequent_confusions expected→detected) and `words`: word, score, t (s) and, when there are
errors, expected/detected in IPA and errors [{type: substitution|deletion|insertion,
expected, detected}]; `missing` when the word was not said. `phonemes` holds both full
sequences. Word score = 100·(1 − (S + D + 0.5·I)/expected phonemes). Allophonic variants
(flap, schwa, linking r) do not count as errors. The text_mismatch warning means a
different text was probably read. Backend: local wav2vec2, or Azure when
VOICE_COACH_PRONUNCIATION_BACKEND=azure (then the audio is sent to Azure).

Input parameters:

- `audio` (string, required)
- `expected_text` (string, required)
- `language` (string)

Output parameters:

- `result` (string)

### `read_progress` (~68 tokens)

Reads the latest sessions from the progress log (~/VoiceCoach/progress.md).

Use it at the start of a session to pick up the previous focus. Returns `file`,
\`total_entries` and `entries` (markdown of each session, oldest to newest).

Input parameters:

- `entries` (integer)

Output parameters:

- `result` (string)

### `log_progress` (~75 tokens)

Appends a session to the progress log (~/VoiceCoach/progress.md).

Args:
    entry: markdown of the session. It should start with "## YYYY-MM-DD · mode · exercise";
        if it does not start with "## ", the date and time are added as the title.

Input parameters:

- `entry` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp#diagnostics

## Score history

- 2026-11-05: 63
- 2026-11-04: 78
- 2026-11-03: 63
- 2026-11-02: 63
- 2026-11-01: 78
- 2026-10-31: 63
- 2026-10-30: 78
- 2026-10-29: 78
- 2026-10-28: 63
- 2026-10-27: 63
- 2026-10-26: 63
- 2026-10-25: 63
- 2026-10-24: 78
- 2026-10-23: 63

## Common questions

### What is the Voice Coach MCP server?

Voice Coach is an MCP server listed in the public MCP registry as io.github.FabianIMV/voice-coach-mcp. Gives Claude ears: local pitch, pronunciation and public-speaking analysis for voice coaching. This page covers its PyPI package (voice-coach-mcp).

### Is the Voice Coach MCP server safe to use?

Voice Coach scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Voice Coach MCP server expose?

Voice Coach exposes 7 tools: record_audio, analyze_pitch, transcribe, speech_metrics, assess_pronunciation, and 2 more. Their descriptions and schemas cost roughly 1,392 tokens of context every time the server is loaded.

### Is the Voice Coach MCP server still maintained?

Voice Coach is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Voice Coach MCP server under?

Voice Coach declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/voice-coach-mcp/
- Socket report: https://socket.dev/pypi/package/voice-coach-mcp
- Repository: https://github.com/FabianIMV/voice-coach-mcp
- Changelog RSS feed: https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp.json
- HTML version of this page: https://verifymcp.io/servers/fabianimv-voice-coach-mcp/voice-coach-mcp