Langlearn TTS

소개

Langlearn TTS is a versatile text-to-speech toolkit designed specifically for language learners. It offers both a robust command-line interface and an MCP server for seamless integration with Claude Desktop, providing identical functionality across both platforms. Currently leveraging AWS Polly, the tool is actively developing support for ElevenLabs and OpenAI TTS, aiming to offer flexible backend choices without requiring an AWS account. It enables users to synthesize single texts, create merged batches, or stitch together translations for paired language practice, with configurable speech rates and support for a wide array of voices and languages.

주요 기능

• 0 GitHub stars
• Single and batch text synthesis into MP3 audio
• Pair synthesis to stitch two languages together with a customizable pause
• Configurable speech rate for learner-friendly pacing (default 90%)
• Auto-play synthesized audio via MCP tools for immediate feedback
• Supports 93 voices and 41 languages from AWS Polly

사용 사례

• Synthesizing vocabulary lists for listening practice
• Creating audio flashcards by stitching together native and target language phrases
• Generating spoken examples of sentences or phrases for language immersion
• Integrating text-to-speech capabilities into Claude Desktop workflows for instant audio conversion