メニュー
Cloud TTS via Replicate for narration, audiobooks, voice cloning, and content creation
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/fabioc-aloha/Alex_Plug_In --skill text-to-speechコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Create and maintain ASCII visual dashboards for project tracking with parallel lane progress bars
Store and manage voice samples for TTS cloning — portable, version-controlled audio references
Clear documentation through visual excellence
SOC 職業分類に基づく
| name | text-to-speech |
| description | Cloud TTS via Replicate for narration, audiobooks, voice cloning, and content creation |
| tier | extended |
| applyTo | **/*tts*,**/*speech*,**/*audio*,**/*narration* |
| $schema | ../SKILL-SCHEMA.json |
Domain: AI Audio Generation
Version: 3.0.0
Last Updated: 2026-04-09
Author: Alex (Master Alex)
Staleness Watch: See EXTERNAL-API-REGISTRY.md for source URLs and recheck cadence
Cloud-based speech synthesis via Replicate for narration, audiobooks, voice cloning, and content creation. Uses paid Replicate TTS models (MiniMax Speech, Chatterbox, Qwen TTS) for high-quality output.
Note: The VS Code extension's built-in Edge TTS feature was removed in v7.4.0. This skill now focuses exclusively on Replicate cloud TTS for script-based audio generation.
| Model | Replicate ID | Cost |
|---|
| Voice Cloning |
|---|
| Languages |
|---|
| Best For |
|---|
| Speech 2.8 Turbo | minimax/speech-2.8-turbo | $0.06/1k tokens | No | 40+ | Fast, expressive, many voices |
| Speech 2.8 HD | minimax/speech-2.8-hd | higher | No | 40+ | Studio-grade high-fidelity |
| Chatterbox Turbo | resemble-ai/chatterbox-turbo | $0.025/1k chars | Yes (5s sample) | English | Voice cloning, natural pauses |
| Qwen TTS | qwen/qwen3-tts | $0.02/1k chars | Yes | 10 | Voice design from description |
Speech Turbo: Wise_Woman, Deep_Voice_Man, Casual_Guy, Lively_Girl, Young_Knight, Abbess, + 6 more
Chatterbox: Andy, Luna, Ember, Aurora, Cliff, Josh, William, Orion, Ken
Qwen TTS: Aiden, Dylan, Eric, Serena, Vivian, + 4 more
Supported emotions: auto, happy, sad, angry, fearful, disgusted, surprised
Provide a 5+ second audio sample to clone a voice:
const output = await replicate.run("resemble-ai/chatterbox-turbo", {
input: {
text: "Content to speak in the cloned voice",
audio_prompt: referenceAudioDataURI, // 5+ seconds WAV/MP3
},
});
Create a voice from a natural language description:
const output = await replicate.run("qwen/qwen3-tts", {
input: {
text: "Content to speak",
tts_mode: "voice_design",
voice_description:
"A warm, friendly female voice with a slight British accent",
},
});
| Scenario | Recommended | Why |
|---|---|---|
| Narration, audiobooks | Speech 2.8 HD | Studio-grade quality, 40+ languages |
| Quick drafts, iteration | Speech 2.8 Turbo | Fast, cheapest per-token |
| Clone a specific voice | Chatterbox Turbo | 5-second sample, natural pauses |
| Voice from description | Qwen TTS | No sample needed, describe the voice |
| Non-English content | Speech 2.8 Turbo/HD | Broadest language support (40+) |
saymacOS ships 30+ built-in neural voices via the say command. Instant, offline, zero-cost. Useful for quick reads and completion notifications.
say "Hello from Alex"
say -f document.txt
say -o output.m4a --data-format=aac "Dream state finished"
say -v Alex "I am Alex, reading your documentation"
Completion notifications for long operations:
node .github/muscles/brain-qa.cjs --mode quick && say "Brain QA complete"
| Use Case | Benefit |
|---|---|
| Vision impaired | Full document access via audio |
| Multitasking | Review code while walking/driving |
| Learning | Auditory reinforcement of reading |
| Proofreading | Catch errors by hearing text |
| Content creation | Generate narration for videos, podcasts |