impressions

impressions is a skill for Claude Code from mbailey/voicemode. It costs 47 tokens per session (1,706 once invoked), scanned A, original, MIT.

A VoiceMode guide for adding custom voices from short reference recordings using local speech synthesis. It is experimental, opt-in, and limited to Apple Silicon computers.

In plain words
What is it for?
Use it to install the local audio service, add a voice from a reference clip, configure a remote service, or speak with a saved custom voice profile.
Why use it?
It explains the extra setup and input requirements needed when a standard voice is not enough.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the voicemode plugin — 5 skills, 3 commands, 1 agent, 5 hooks, 1 MCP server shipped together

About the project

VoiceMode adds natural spoken conversations to Claude Code and other agents that support MCP. Developers use it when their hands or eyes are busy, with optional local speech services for offline or privacy-focused use, and the catalogue provides skills, hooks, commands, plugins, instructions, agents, settings, and MCP integration for the workflow.

mbailey/voicemode · 1,349 stars · on GitHub · voicemode.dev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mbailey/voicemode/impressions
Any agent
npx skills add mbailey/voicemode --skill impressions
Clone the repo
git clone --depth 1 https://github.com/mbailey/voicemode

Made for: Claude Code.

Or install voicemode, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 1 agent, 5 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for impressions

README.md
[![agentmods](https://agentmods.dev/badge/skills/mbailey/voicemode/impressions.svg)](https://agentmods.dev/skills/mbailey/voicemode/impressions)
Your own site
<a href="https://agentmods.dev/skills/mbailey/voicemode/impressions"><img src="https://agentmods.dev/badge/skills/mbailey/voicemode/impressions.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.01706
Opus 5 $0.00023 $0.00853
Sonnet 5 $0.00009 $0.00341
Haiku 4.5 $0.00005 $0.00171

Measured 6d ago against content hash 1378fb273b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

impressions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/impressions/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Impressions

Make VoiceMode speak in any voice. The model takes a short reference clip and synthesises fresh speech in that voice via local Qwen3-TTS on top of mlx-audio.

Status: Preview / experimental. Apple Silicon only. Opt-in.

When to use this skill

  • User asks for "voice cloning", "do an impression", "speak as X", "add my voice"
  • A voice= argument in voicemode:converse doesn't match a known Kokoro voice
  • User wants to install or troubleshoot the mlx-audio service
  • User asks how to configure a remote mlx-audio server

Quick start

# 1. Install the local TTS service (one-time, Apple Silicon only)
voicemode service install mlx-audio

# 2. Add a voice from a reference clip
voicemode clone add fleabag ~/Downloads/fleabag-clip.wav

# 3. Use it
voicemode converse --voice fleabag

In the MCP converse tool, pass voice="fleabag" -- VoiceMode auto-routes any voice that matches a profile in VOICEMODE_VOICES_DIR to mlx-audio instead of Kokoro / OpenAI.

Reference clip requirements

voicemode clone add validates the input before doing any expensive work:

  • Duration: 3-9 seconds (5-9s sweet spot). Clips outside this window are rejected with an actionable error.
  • Mono speech, no music or cross-talk. The model copies what it hears -- including hum, music beds, laugh tracks, and overlapping speakers.
  • Any input format accepted. WAV, MP3, M4A, etc. -- ffmpeg normalises whatever you hand it.
  • Output is always mono 24 kHz 16-bit PCM with loudnorm I=-16 TP=-1.5 LRA=11. This is the canonical voice-lab format; the original input is replaced by this normalised render at default.wav.
  • ALWAYS pair the clip with its transcript. The model conditions on the reference text; without one it ASRs the clip itself, and any mis-hearing (noisy or vintage audio especially) corrupts the conditioning -- the symptom is stammering / stuttered synthesis. voicemode clone add auto-transcribes into voice.md (verify it -- correct mis-hearings by hand); voice-lab's sayas reads <clip>.txt next to each wav; the MCP converse tool takes ref_text alongside a clip-path voice. (Root-caused on VL-50, 2026-06-11: 1977 Doctor Who clips stammered until transcripts were supplied -- then "much better!!!".)

Read the full file on GitHub · 110 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 110 lines · 47 tokens per session scan A 1378fb273b67

Subscribe to this mod's changes

impressions is a skill published in the GitHub repository mbailey/voicemode (1,349 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 1,706 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories