config-voice

config-voice is a skill for Claude Code from vibesurf-ai/claude-surf. It costs 53 tokens per session (1,522 once invoked), scanned A, original, MIT.

Voice-profile and speech-to-text configuration for VibeSurf. Speech-to-text, also called automatic speech recognition, turns recorded audio into written words using supported providers such as Whisper, Qwen, or Gemini.

In plain words
What is it for?
Use it to create or update voice profiles, choose recognition providers and models, view available models, and convert audio files into text.
Why use it?
It removes the need to configure voice settings and recognition services separately for each audio task.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the surf plugin — 21 skills, 1 hook shipped together

Good fit Use it to create or update voice profiles, choose recognition providers and models, view available models, and convert audio files into text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vibesurf-ai/claude-surf/config-voice
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.

Any agent
npx skills add vibesurf-ai/claude-surf --skill config-voice
Clone the repo
git clone --depth 1 https://github.com/vibesurf-ai/claude-surf

Made for: Claude Code.

Or install surf, the plugin that ships this one along with the rest of its 21 skills, 1 hook.

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 config-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/config-voice/github.svg)](https://agentmods.dev/skills/vibesurf-ai/claude-surf/config-voice)
Your own site
<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/config-voice"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/config-voice/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for config-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/config-voice"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/config-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00053 $0.01522
Opus 5 $0.00026 $0.00761
Sonnet 5 $0.00011 $0.00304
Haiku 4.5 $0.00005 $0.00152

Measured 12d ago against content hash 7d31a41b4c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

config-voice 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 12d 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.

skills/config-voice/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Config Voice - Voice Profile & ASR Management

Overview

Manage voice profiles for VibeSurf. Configure ASR (Automatic Speech Recognition) providers, models, and perform speech-to-text conversion.

Supported ASR providers:

  • qwen-asr - Alibaba Qwen ASR models
  • openai-asr - OpenAI Whisper API
  • gemini-asr - Google Gemini ASR

When to Use

  • User wants to add a new voice profile for ASR
  • User needs to configure speech-to-text settings
  • User wants to update voice profile settings (API key, model params, etc.)
  • User needs to list or manage existing voice profiles
  • User wants to perform voice recognition (ASR) on an audio file
  • User wants to see available voice models

API Endpoints

Base path: $VIBESURF_ENDPOINT/api/voices

Voice Profile Management

Action Method Endpoint Description
List Profiles GET /api/voices/voice-profiles?active_only=true List all voice profiles
Get Profile GET /api/voices/{voice_profile_name} Get specific profile details
Create Profile POST /api/voices/voice-profiles Create new voice profile
Update Profile PUT /api/voices/voice-profiles/{voice_profile_name} Update existing profile

ASR (Speech Recognition)

Action Method Endpoint Description
Perform ASR POST /api/voices/asr Transcribe audio file to text

Model Management

Action Method Endpoint Description
List Models GET /api/voices/models Get available voice models

Request Examples

Create ASR Profile

POST /api/voices/voice-profiles
{
  "voice_profile_name": "my-qwen-asr",
  "voice_model_type": "asr",
  "voice_model_name": "qwen-asr",
  "api_key": "sk-...",
  "voice_meta_params": {
    "asr_model_name": "qwen-audio-asr-latest"
  },
  "description": "Qwen ASR for Chinese speech recognition"
}

Create OpenAI Whisper Profile

Read the full file on GitHub · 180 lines

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. 12d ago First seen · 180 lines · 53 tokens per session scan A 7d31a41b4c1a

Subscribe to this mod's changes

config-voice is a skill published in the GitHub repository vibesurf-ai/claude-surf (24 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 1,522 once invoked, about $0.0003 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.