feishu-edge-tts_skill

Overview

This skill uses Microsoft Edge TTS to generate high-quality voice messages and send them directly to Feishu chats. It requires no API key and supports many languages and voices, with controls for speed and pitch. The output is a native Feishu voice message that plays on click. It is designed for automated notifications, greetings, and multilingual announcements.

How this skill works

The skill calls the edge-tts engine to synthesize text into audio using selected neural voices and parameters for rate and pitch. It can produce MP3/WAV output and then uploads the file to Feishu, creating a playable voice message in the target chat. The scripts include options to list available voices, batch-process lines from a file, and skip sending if you only need local audio files.

When to use it

• Send voice notifications or reminders to a Feishu team or chat without paying for TTS APIs.
• Create multilingual voice messages for users who prefer audio over text.
• Automate daily or scheduled voice announcements (news, status, alerts).
• Generate prototype or demo voice outputs during development.
• Produce fun or localized messages using regional dialect voices.

Best practices

• Test different neural voices to match tone and clarity for your audience.
• Keep messages concise for clear playback on mobile devices.
• Use rate and pitch adjustments sparingly to maintain naturalness.
• Batch-generate audio with pauses between uploads to avoid rate limits.
• Install ffmpeg to ensure broad audio format compatibility.

Example use cases

• Morning greeting to a team chat using a warm female Chinese voice.
• Automated English status update using an American English neural voice.
• Broadcast a short company announcement to multiple group chats.
• Create localized, humorous messages using regional dialect voices.
• Generate and store voice versions of system alerts for accessibility.