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 ID |
Name |
Gender |
Language/Style |
| 1 |
zh-CN-XiaoxiaoNeural |
Xiaoxiao ⭐ |
Female |
Mandarin, warm and natural |
| 2 |
zh-CN-XiaoyiNeural |
Xiaoyi |
Female |
Mandarin, lively and playful |
| 3 |
zh-CN-YunxiNeural |
Yunxi |
Male |
Mandarin, cheerful and energetic |
| 4 |
zh-CN-YunjianNeural |
Yunjian |
Male |
Mandarin, passionate and powerful |
| 5 |
zh-CN-YunyangNeural |
Yunyang |
Male |
Mandarin, professional and reliable |
| 6 |
zh-CN-YunxiaNeural |
Yunxia |
Male |
Mandarin, cute and charming |
| 7 |
zh-CN-liaoning-XiaobeiNeural |
Xiaobei |
Female |
Northeastern Chinese, humorous and friendly |
| 8 |
zh-CN-shaanxi-XiaoniNeural |
Xiaoni |
Female |
Shaanxi dialect, bright and cheerful |
| 9 |
zh-HK-HiuGaaiNeural |
HiuGaai |
Female |
Cantonese, friendly |
| 10 |
zh-HK-HiuMaanNeural |
HiuMaan |
Female |
Cantonese, friendly |
| 11 |
zh-HK-WanLungNeural |
WanLung |
Male |
Cantonese, friendly |
| 12 |
zh-TW-HsiaoChenNeural |
HsiaoChen |
Female |
Taiwan Mandarin, friendly |
| 13 |
zh-TW-HsiaoYuNeural |
HsiaoYu |
Female |
Taiwan Mandarin, friendly |
| 14 |
zh-TW-YunJheNeural |
YunJhe |
Male |
Taiwan 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
| Parameter |
Description |
Default Value |
--text |
Text to synthesize (required) |
N/A |
--write-media |
Output MP3 file path (required) |
N/A |
--voice |
Voice ID |
zh-CN-XiaoxiaoNeural |
--rate |
Speech rate adjustment percentage |
0% |
--volume |
Volume adjustment percentage |
0% |
--pitch |
Pitch adjustment |
0Hz |
Output Format
Return an MP3 file link that the user can click to play, in this format:
Shortcuts
| User Input |
Action |
| "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
- The user requests that text be read aloud or says "Read it"
- Determine the target voice (specified by the user or the current default)
- Call
edge-tts to synthesize an MP3 at /var/minis/workspace/free_tts_<timestamp>.mp3
- 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.
1---2name: free-tts3description: 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.4---56# Free TTS Skill78Use `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**.910## Environment Dependencies1112```sh13pip install edge-tts14```1516No API key, account, or token is required.1718## Complete List of Chinese Voices1920| # | Voice ID | Name | Gender | Language/Style |21|:-:|---------|------|:----:|-----------|22| 1 | `zh-CN-XiaoxiaoNeural` | Xiaoxiao ⭐ | Female | Mandarin, warm and natural |23| 2 | `zh-CN-XiaoyiNeural` | Xiaoyi | Female | Mandarin, lively and playful |24| 3 | `zh-CN-YunxiNeural` | Yunxi | Male | Mandarin, cheerful and energetic |25| 4 | `zh-CN-YunjianNeural` | Yunjian | Male | Mandarin, passionate and powerful |26| 5 | `zh-CN-YunyangNeural` | Yunyang | Male | Mandarin, professional and reliable |27| 6 | `zh-CN-YunxiaNeural` | Yunxia | Male | Mandarin, cute and charming |28| 7 | `zh-CN-liaoning-XiaobeiNeural` | Xiaobei | Female | Northeastern Chinese, humorous and friendly |29| 8 | `zh-CN-shaanxi-XiaoniNeural` | Xiaoni | Female | Shaanxi dialect, bright and cheerful |30| 9 | `zh-HK-HiuGaaiNeural` | HiuGaai | Female | Cantonese, friendly |31|10 | `zh-HK-HiuMaanNeural` | HiuMaan | Female | Cantonese, friendly |32|11 | `zh-HK-WanLungNeural` | WanLung | Male | Cantonese, friendly |33|12 | `zh-TW-HsiaoChenNeural` | HsiaoChen | Female | Taiwan Mandarin, friendly |34|13 | `zh-TW-HsiaoYuNeural` | HsiaoYu | Female | Taiwan Mandarin, friendly |35|14 | `zh-TW-YunJheNeural` | YunJhe | Male | Taiwan Mandarin, friendly |3637To view the complete list of multilingual voices, run `edge-tts --list-voices`.3839## Usage4041```sh42# Default voice (Xiaoxiao)43edge-tts --text "Hello, and welcome to our free text-to-speech service." --write-media /var/minis/workspace/output.mp34445# Specify a voice46edge-tts --voice zh-CN-XiaoyiNeural --text "The weather is really nice today." --write-media /var/minis/workspace/output.mp34748# Adjust speech rate and volume (percentage, -50 ~ +100)49edge-tts --voice zh-CN-XiaoxiaoNeural --rate=+20% --volume=+50% \50 --text "Welcome to today's news." --write-media /var/minis/workspace/output.mp351```5253### Parameter Description5455| Parameter | Description | Default Value |56|------|------|-------|57| `--text` | Text to synthesize (required) | N/A |58| `--write-media` | Output MP3 file path (required) | N/A |59| `--voice` | Voice ID | `zh-CN-XiaoxiaoNeural` |60| `--rate` | Speech rate adjustment percentage | `0%` |61| `--volume` | Volume adjustment percentage | `0%` |62| `--pitch` | Pitch adjustment | `0Hz` |6364## Output Format6566Return an MP3 file link that the user can click to play, in this format:6768```6970```7172## Shortcuts7374| User Input | Action |75|----------|------|76| "Read it" / "Read aloud" | Synthesize and play using the default voice (Xiaoxiao) |77| "Use a male voice" | Switch to YunJhe (Taiwan Mandarin male voice) |78| "Change" | Cycle to the next voice in the list |79| "Switch to a dialect" | Switch to Xiaoni (Shaanxi dialect) |80| "Switch to Cantonese" / "Speak Cantonese" | Switch to WanLung (Cantonese) |81| "Restore default" | Return to Xiaoxiao |8283## Complete Workflow84851. The user requests that text be read aloud or says "Read it"862. Determine the target voice (specified by the user or the current default)873. Call `edge-tts` to synthesize an MP3 at `/var/minis/workspace/free_tts_<timestamp>.mp3`884. Return an audio link for the user to play8990## Notes9192- **Synthesis speed**: About 1 to 2 seconds per sentence93- **Internet connection required**: Cloud-based synthesis through the Microsoft Edge TTS online interface94- **Zero cost**: No account or payment required95- **Output format**: 24 kHz, 160 kbps MP396- English and other non-Chinese voices can also speak Chinese, but their accents are not standard, so they are not recommended.
openminis