Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cnadiminti/remotion-video-studionpx agentmods add skills/cnadiminti/remotion-video-studio/tts-integrationWrote 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.
[](https://agentmods.dev/skills/cnadiminti/remotion-video-studio/tts-integration)<a href="https://agentmods.dev/skills/cnadiminti/remotion-video-studio/tts-integration"><img src="https://agentmods.dev/badge/skills/cnadiminti/remotion-video-studio/tts-integration/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.
<a href="https://agentmods.dev/skills/cnadiminti/remotion-video-studio/tts-integration"><img src="https://agentmods.dev/badge/skills/cnadiminti/remotion-video-studio/tts-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.03766 |
| Opus 5 | $0.00022 | $0.01883 |
| Sonnet 5 | $0.00009 | $0.00753 |
| Haiku 4.5 | $0.00004 | $0.00377 |
Grade A, and why
tts-integration scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text-to-Speech Integration Skill
Expert knowledge in integrating multiple TTS providers with Remotion for video narration.
Overview
This skill covers integrating Text-to-Speech services with Remotion video projects, including Mac TTS, Google Cloud TTS, Azure TTS, and ElevenLabs.
TTS Provider Comparison
Mac TTS (Built-in)
- API: macOS
saycommand - Cost: FREE
- Quality: Good (7/10)
- Latency: Low (local)
- Languages: 40+
- Voices: 70+ including Siri voices
- Best voices: Zoe (US), Samantha (US), Alex (US), Anna (German)
Google Cloud TTS
- API: @google-cloud/text-to-speech
- Cost: $4 per 1M characters
- Quality: Very Good (8/10)
- Latency: Medium (cloud)
- Languages: 40+
- Voices: 400+ Neural2 voices
- Best for: Production, cost-effective
Azure TTS
- API: microsoft-cognitiveservices-speech-sdk
- Cost: $16 per 1M characters
- Quality: Very Good (8/10)
- Latency: Medium (cloud)
- Languages: 75+
- Voices: 400+ Neural voices
- Best for: Enterprise, Microsoft ecosystem
ElevenLabs
- API: elevenlabs SDK
- Cost: $5-99/month or ~$0.20/1K chars
- Quality: Excellent (10/10)
- Latency: Medium (cloud)
- Languages: 29+
- Voices: 100+ plus custom clones
- Best for: Premium quality, voice cloning
Mac TTS Integration
Basic Implementation
// src/utils/tts-mac.ts
import { execSync } from 'child_process';
import { existsSync, mkdirSync } from 'fs';
import path from 'path';
export interface MacTTSOptions {
voice?: string;
rate?: number; // Words per minute (default: 180)
quality?: number; // 0-127 (default: 127)
outputDir?: string;
}
export async function generateMacTTS(
text: string,
options: MacTTSOptions = {}
): Promise<string> {
const {
voice = 'Zoe',
rate = 180,
quality = 127,
outputDir = './public/audio'
} = options;
// Ensure output directory exists
if (!existsSync(outputDir)) {
mkdirSync(outputDir, { recursive: true });
}
// Generate unique filename
const timestamp = Date.now();
const filename = `mac-tts-${timestamp}.aiff`;
const outputPath = path.join(outputDir, filename);
// Escape text for shell
const escapedText = text.replace(/"/g, '\\"');
// Generate audio
try {
execSync(
`say -v "${voice}" -r ${rate} -o "${outputPath}" --quality=${quality} "${escapedText}"`,
{ stdio: 'pipe' }
);
// Convert AIFF to MP3 for better compatibility
const mp3Path = outputPath.replace('.aiff', '.mp3');
execSync(`ffmpeg -i "${outputPath}" -acodec libmp3lame -ab 192k "${mp3Path}"`, {
stdio: 'pipe'
});
// Remove AIFF file
execSync(`rm "${outputPath}"`);
return mp3Path;
} catch (error) {
throw new Error(`Mac TTS generation failed: ${error.message}`);
}
}
// Get available voices
export function getMacVoices(): string[] {
try {
const output = execSync('say -v "?"', { encoding: 'utf-8' });
const voices = output
.split('\n')
.filter(line => line.trim())
.map(line => line.split(/\s+/)[0]);
return voices;
} catch {
return ['Zoe', 'Samantha', 'Alex']; // Fallback
}
}
// Get audio duration
export function getAudioDuration(filePath: string): number {
try {
const output = execSync(
`ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "${filePath}"`,
{ encoding: 'utf-8' }
);
return parseFloat(output.trim());
} catch {
return 0;
}
}
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.
- 12d ago First seen · 608 lines · 44 tokens per session scan A e7b9a068fe2c
tts-integration is a skill published in the GitHub repository cnadiminti/remotion-video-studio (2 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 3,766 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…