agentleFS
Sign inStart free
OpenMinisOpenMinis/MinisSkills/free-tts/SKILL.md

free-tts

Skill584 starsChanged 59 days agoMITView on GitHub

Free text-to-speech (edge-tts), with no API key or registration required. Converts text to MP3 audio files. Trigger this skill when the user says "read aloud," "text-to-speech," "TTS," "generate audio," "read it," "read it out loud," "say it," "play it," or in any scenario where text needs to be converted to speech for playback.

  • Installs packages

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use edge-tts (a Python library) to convert text to an MP3 audio file.

    line 12
  2. Distinctive:

    No API key, account, or token is required.

    line 20
  3. Very specific:

    Call edge-tts to synthesize an MP3 at /var/minis/workspace/free_tts_<timestamp>.mp3

    line 91
  4. Distinctive:

    Zero cost: No account or payment required

    line 98

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Free TTS Skill

Use edge-tts (a Python library) to convert text to an MP3 audio file. It calls the Microsoft Edge browser's online TTS interface in the background. It is completely free, requires no registration, needs no configuration, has unlimited usage, and connects directly from within China.

Environment Dependencies

pip install edge-tts

No API key, account, or token is required.

Complete List of Chinese Voices

#Voice IDNameGenderLanguage/Style
1zh-CN-XiaoxiaoNeuralXiaoxiao ⭐FemaleMandarin, warm and natural
2zh-CN-XiaoyiNeuralXiaoyiFemaleMandarin, lively and playful
3zh-CN-YunxiNeuralYunxiMaleMandarin, cheerful and energetic
4zh-CN-YunjianNeuralYunjianMaleMandarin, passionate and powerful
5zh-CN-YunyangNeuralYunyangMaleMandarin, professional and reliable
6zh-CN-YunxiaNeuralYunxiaMaleMandarin, cute and charming
7zh-CN-liaoning-XiaobeiNeuralXiaobeiFemaleNortheastern Chinese, humorous and friendly
8zh-CN-shaanxi-XiaoniNeuralXiaoniFemaleShaanxi dialect, bright and cheerful
9zh-HK-HiuGaaiNeuralHiuGaaiFemaleCantonese, friendly
10zh-HK-HiuMaanNeuralHiuMaanFemaleCantonese, friendly
11zh-HK-WanLungNeuralWanLungMaleCantonese, friendly
12zh-TW-HsiaoChenNeuralHsiaoChenFemaleTaiwan Mandarin, friendly
13zh-TW-HsiaoYuNeuralHsiaoYuFemaleTaiwan Mandarin, friendly
14zh-TW-YunJheNeuralYunJheMaleTaiwan Mandarin, friendly

To view the complete list of multilingual voices, run edge-tts --list-voices.

Usage

# Default voice (Xiaoxiao)
edge-tts --text "Hello, and welcome to our free text-to-speech service." --write-media /var/minis/workspace/output.mp3

# Specify a voice
edge-tts --voice zh-CN-XiaoyiNeural --text "The weather is really nice today." --write-media /var/minis/workspace/output.mp3

# Adjust speech rate and volume (percentage, -50 ~ +100)
edge-tts --voice zh-CN-XiaoxiaoNeural --rate=+20% --volume=+50% \
  --text "Welcome to today's news." --write-media /var/minis/workspace/output.mp3

Parameter Description

ParameterDescriptionDefault Value
--textText to synthesize (required)N/A
--write-mediaOutput MP3 file path (required)N/A
--voiceVoice IDzh-CN-XiaoxiaoNeural
--rateSpeech rate adjustment percentage0%
--volumeVolume adjustment percentage0%
--pitchPitch adjustment0Hz

Output Format

Return an MP3 file link that the user can click to play, in this format:

![Audio](minis://workspace/free_tts_<timestamp>.mp3)

Shortcuts

User InputAction
"Read it" / "Read aloud"Synthesize and play using the default voice (Xiaoxiao)
"Use a male voice"Switch to YunJhe (Taiwan Mandarin male voice)
"Change"Cycle to the next voice in the list
"Switch to a dialect"Switch to Xiaoni (Shaanxi dialect)
"Switch to Cantonese" / "Speak Cantonese"Switch to WanLung (Cantonese)
"Restore default"Return to Xiaoxiao

Complete Workflow

  1. The user requests that text be read aloud or says "Read it"
  2. Determine the target voice (specified by the user or the current default)
  3. Call edge-tts to synthesize an MP3 at /var/minis/workspace/free_tts_<timestamp>.mp3
  4. Return an audio link for the user to play

Notes

  • Synthesis speed: About 1 to 2 seconds per sentence
  • Internet connection required: Cloud-based synthesis through the Microsoft Edge TTS online interface
  • Zero cost: No account or payment required
  • Output format: 24 kHz, 160 kbps MP3
  • English and other non-Chinese voices can also speak Chinese, but their accents are not standard, so they are not recommended.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free