audiobash: Command for Claude Code

.claude/commands/transcription-provider.md

transcription-provider is a command for Claude Code from jamditis/audiobash. It costs 0 tokens per session (1,045 once invoked), scanned B, original, MIT.

A code-generation guide for adding speech-to-text services to AudioBash, an application that turns recorded audio into written text. It covers the model list, audio formats, provider methods, and routing used by the app.

In plain words
What is it for?
Use it when adding a new speech-to-text provider or model to AudioBash's TranscriptionService.
Why use it?
It gives developers the required places and conventions for a new provider, reducing the chance of an incomplete integration.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is jamditis/audiobash's own configuration. It tells Claude Code how to work on audiobash itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything audiobash configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jamditis/audiobash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jamditis/audiobash/master/.claude/commands/transcription-provider.md
Clone the repo
git clone --depth 1 https://github.com/jamditis/audiobash

Made for: Claude Code.

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 transcription-provider

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamditis/audiobash/transcription-provider/github.svg)](https://agentmods.dev/commands/jamditis/audiobash/transcription-provider)
Your own site
<a href="https://agentmods.dev/commands/jamditis/audiobash/transcription-provider"><img src="https://agentmods.dev/badge/commands/jamditis/audiobash/transcription-provider/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 transcription-provider

Your own site · 80×15
<a href="https://agentmods.dev/commands/jamditis/audiobash/transcription-provider"><img src="https://agentmods.dev/badge/commands/jamditis/audiobash/transcription-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.01045
Opus 5 $0.00000 $0.00522
Sonnet 5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00104

Measured 9d ago against content hash 8ae6185c41cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

transcription-provider scanned grade B with 1 finding 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 9d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch('https://api.newprovider.com/transcribe', { method: 'POST',
.claude/commands/transcription-provider.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transcription Provider Generator

You are an AI/ML engineer adding speech-to-text providers to AudioBash's TranscriptionService.

Your Expertise

You understand:

  • Audio encoding (WebM from MediaRecorder, WAV from VAD, base64 for APIs)
  • The TranscriptionService architecture (550 lines, 6 providers)
  • Provider method naming: transcribeWith{Provider}()
  • The ModelId type union and MODELS array
  • Agent mode vs raw mode routing

Current Architecture

// src/services/transcriptionService.ts

export type ModelId =
  | 'gemini-2.0-flash' | 'gemini-2.5-flash'
  | 'openai-whisper' | 'openai-gpt4'
  | 'claude-sonnet' | 'claude-haiku'
  | 'elevenlabs-scribe'
  | 'parakeet-local'
  | 'whisper-local-tiny' | 'whisper-local-base' | 'whisper-local-small';

export const MODELS: ModelInfo[] = [
  { id: 'gemini-2.0-flash', name: 'Gemini 2.0 Flash', provider: 'gemini', description: 'Fast, native audio', supportsAgent: true },
  // ... more models
];

To Add a New Provider

Generate these 4 pieces:

1. ModelId Addition

// Add to the ModelId type union
| 'newprovider-model'

2. MODELS Entry

// Add to MODELS array
{
  id: 'newprovider-model',
  name: 'NewProvider Model',
  provider: 'newprovider',
  description: 'Brief description',
  supportsAgent: false  // true if LLM-based
},

3. Provider Method

private async transcribeWithNewProvider(
  audioBlob: Blob,
  mode: TranscriptionMode,
  modelId: ModelId,
  durationMs: number
): Promise<TranscribeResult> {
  const apiKey = this.apiKeys.get('newprovider');
  if (!apiKey) {
    throw new Error('NewProvider API key not configured');
  }

  // Convert audio to required format
  const base64Audio = await blobToBase64(audioBlob);
  // OR for FormData APIs:
  // const formData = new FormData();
  // formData.append('audio', audioBlob, 'audio.webm');

  const response = await fetch('https://api.newprovider.com/transcribe', {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${apiKey}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      audio: base64Audio,
      // Provider-specific options
    }),
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.message || 'NewProvider API error');
  }

  const data = await response.json();
  const text = data.transcript || data.text || '';
  const cost = this.calculateCost(durationMs, 'newprovider');

  return { text: text.trim(), cost };
}

Read the full file on GitHub · 151 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. 9d ago First seen · 151 lines · 0 tokens per session scan B 8ae6185c41cd

Subscribe to this mod's changes

transcription-provider is a command published in the GitHub repository jamditis/audiobash (6 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,045 tokens. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.