Convert text to MP3 speech audio using the edge-tts command-line tool.
npx skills add https://github.com/riipandi/minis-skills --skill free-tts-riipandi
Please help me install this Agent Skill. Skill: free-tts Source: https://github.com/riipandi/minis-skills/tree/main/free-tts Command: npx skills add https://github.com/riipandi/minis-skills --skill free-tts-riipandi
edge-tts --list-voices. - Adjustable Playback Parameters: Control speech rate, volume, and pitch with simple percentage or Hz adjustments. - Use Case: A user pastes a long article and says "read it aloud" — the skill synthesizes the text into an MP3 file and returns a clickable audio link for immediate playback. ## Quick Start Ask the assistant to read the provided text aloud and it will generate a playable MP3 audio file using the default Xiaoxiao voice.High-intent search queries and answers about installing and using this skill.
Install the edge-tts Python package and run it with a --text argument and --write-media output path. It calls the Microsoft Edge online TTS API, which requires no API key, account, or payment.
Run edge-tts with --text for the content and --write-media for the output MP3 path, optionally adding --voice, --rate, --volume, and --pitch. Synthesis takes about 1-2 seconds per sentence and outputs 24kHz 160kbps MP3.
edge-tts offers 14 Chinese voices including Mandarin (Xiaoxiao, Yunxi, Yunjian), Cantonese (HiuGaai, WanLung), Taiwan Mandarin (HsiaoChen, YunJhe), and dialects like Dongbei and Shaanxi. Run edge-tts --list-voices for the full multilingual list.
edge-tts requires an internet connection because it performs cloud synthesis through the Microsoft Edge online TTS API. It cannot generate speech audio without network access.
Pass --rate and --volume as percentage adjustments, such as --rate=+20% or --volume=+50%, with a range from -50% to +100%. Pitch can be adjusted with --pitch in Hz, for example --pitch=+10Hz.
Tommy-ywTranscribe spoken audio to text in 99 languages using OpenAI's Whisper model.
yudameConvert podcast audio to MP3, transcribe locally with Whisper, and embed chapter metadata.
akunikkolaApply official Finnish spelling, grammar, and style rules to text.
Moshe-shipSynthesizes Saudi Arabic speech from text using NAMAA-Saudi-TTS, Lahajati, or Voxtral/Mistral TTS with optional voice cloning.