english-pronunciation-audio
This skill generates TTS audio for English pronunciation practice within Telegram, designed to complement `english-daily-coach`. It automatically extracts English sentences from coaching replies or user queries and provides high-quality audio files. Especially when users ask 'how to pronounce X', the skill directly offers audio instead of text-based explanations, significantly streamlining the pronunciation lookup process and helping users practice spoken English more efficiently and naturally.
npx skills add cxwqs/english-coach-telegram --skill english-pronunciation-audioBefore / After Comparison
1 组Previously, users practicing English in Telegram often had to manually copy unfamiliar words or sentences to external pronunciation tools, then switch back to Telegram. This fragmented workflow disrupted learning continuity, making pronunciation practice inefficient and hindering the development of immediate feedback loops.
Now, when users ask 'how to pronounce X' or receive coaching replies in Telegram, this skill automatically generates and sends audio for English sentences. Users can instantly hear standard pronunciation without leaving the chat, significantly simplifying the lookup process and making practice more fluid, thereby boosting learning efficiency and experience.
name: english-pronunciation-audio description: Generate TTS audio for English practice replies and send via Telegram. Use together with english-daily-coach. Extracts spoken English lines, skips Chinese, and sends one audio file per reply. When user asks "怎么读", generate audio for the English sentence — do NOT explain pronunciation in text.
English Pronunciation Audio
CRITICAL Rules
- This skill generates AUDIO files only. NEVER output text-based pronunciation guides (e.g. "vuh-LOR-unt", IPA symbols).
- When user asks "X怎么读" (how to pronounce the sentence they sent): Pass ONLY the exact sentence X the user gave you. Example: user says "What would you like to order for lunch today?怎么读" → exec with
--text "What would you like to order for lunch today". Do NOT pass your reply or any extra text. - When sending coaching reply: Pass the full draft (你说/➡️/💬/📚/🎯) so the script extracts translation + examples + question.
- Generate at most one audio file per reply.
- Skip Chinese lines (lines starting with
提示:,你说:,📚,💬). - Skip
You said:lines. Only readMore natural:andReusable phrase:lines. - Skip vocabulary definitions (
• word — 释义) and phonetic lines (IPA, "pronounced", "vuh-LOR-unt"). - If the user ends the session, skip audio for the final reply.
Supported Reply Shapes
Spoken content is extracted from:
➡️line (translation)①②③lines (example sentences)- Line after
🎯 我会这样继续问你：(follow-up question) Translation:/You can say:/Now you try:/More natural:/Reusable phrase:(legacy labels)
Script
- Use
scripts/tts_openrouter.py. - Pass the full draft reply text with
--text. The script extracts spoken English automatically. - Config:
assets/tts-config.json. - If script returns
no_spoken_textortoo_long, send text reply only. - If script fails, do not block the text reply. Retry at most once.
Reply Shaping
- Keep extracted English under 300 characters total.
- Keep Chinese on separate
提示:lines. - One template per reply for deterministic extraction.
Debugging
--extract-only: inspect extracted English as JSON.--dry-run: generate audio but skip Telegram upload.- To verify what audio will be sent:
python3 scripts/tts_openrouter.py --text "your text" --extract-only
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill