japanese-tts-reading

Convert Japanese text into speech audio using macOS say, Google Cloud TTS, VOICEVOX, or OpenAI TTS.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/sakamotomomotaro0809-netizen/tateyomi --skill japanese-tts-reading-sakamotomomotaro0809-netizen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: japanese-tts-reading
Source: https://github.com/sakamotomomotaro0809-netizen/tateyomi/tree/main/taisun_agent/.claude/skills/japanese-tts-reading
Command: npx skills add https://github.com/sakamotomomotaro0809-netizen/tateyomi --skill japanese-tts-reading-sakamotomomotaro0809-netizen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-cloud-texttospeech, requests.

What problem does it solve? Converting Japanese text into natural-sounding spoken audio requires choosing and configuring a text-to-speech engine, which involves different setup steps, voices, and APIs for each platform. This Skill consolidates four TTS engines into one workflow so you can generate narration, podcast audio, or accessibility audio without researching each service. ## Core Features & Use Cases - Multiple TTS Engines: Use macOS say (local, free), Google Cloud Text-to-Speech (Neural2/WaveNet voices), VOICEVOX (open-source Japanese character voices), or OpenAI TTS. - Flexible Output: Save audio as MP3, WAV, or AIFF, with adjustable speaking rate and voice selection. - Use Case: Turn a sales video narration script into a high-quality audio file by selecting the Google Neural2 voice, generating the speech, and exporting it as MP3 for video editing. ## Quick Start Ask the assistant to read the Japanese text aloud and save it as an MP3 file using the default macOS Kyoko voice.

Frequently Asked Questions about japanese-tts-reading

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert Japanese text to speech on macOS?▼

Use the built-in say command with a Japanese voice such as Kyoko or Otoya, for example say -v Kyoko -o output.aiff followed by your text. You can convert the AIFF result to MP3 with ffmpeg if needed.

Which Japanese TTS engine should I use for high-quality narration?▼

Google Cloud Text-to-Speech with ja-JP-Neural2 voices offers the highest quality for professional narration. VOICEVOX is a free local alternative with Japanese character voices, while macOS say works instantly without setup.

Does VOICEVOX text-to-speech work offline?▼

Yes, VOICEVOX runs locally via a Docker container exposing an HTTP API on port 50021. Once the engine container is running, audio synthesis works without an internet connection.

Why is no Japanese voice available in the macOS say command?▼

Japanese voices may not be downloaded by default. Open macOS speech settings to download them, then verify availability by running say -v '?' and filtering for ja_JP entries.

What output audio formats does Japanese TTS support?▼

The supported output formats are MP3, WAV, and AIFF depending on the engine. macOS say produces AIFF natively, Google TTS and OpenAI TTS return MP3, and VOICEVOX returns WAV.