mirror of
https://github.com/santinic/audiblez.git
synced 2025-09-18 21:40:39 +00:00
samples
This commit is contained in:
Claudio Santini
parent
258b95e219
commit
de81b2c86c
1 changed files with 37 additions and 16 deletions
53
README.md
53
README.md
|
|
@ -20,6 +20,25 @@ On a Google Colab's T4 GPU via Cuda, **it takes about 5 minutes to convert "Anim
|
|||
|
||||
On my M2 MacBook Pro, on CPU, it takes about 1 hour, at a rate of about 60 characters per second.
|
||||
|
||||
## Voices Samples
|
||||
|
||||
These are some samples of the voices available in Audiblez:
|
||||
|
||||
| Voice | Sample | Audio |
|
||||
|-------------------------|-----------|-------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| American English male | af_heart | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_af_heart.mp4?raw=true"></audio> |
|
||||
| American English female | af_bella | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_af_bella.mp4?raw=true"></audio> |
|
||||
| British English female | bf_emma | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_bf_emma.mp4?raw=true"></audio> |
|
||||
| British English male | bm_george | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_bm_george.mp4?raw=true"></audio> |
|
||||
| Spanish female | ef_dora | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_ef_dora.mp4?raw=true"></audio> |
|
||||
| Spanish male | em_alex | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_em_alex.mp4?raw=true"></audio> |
|
||||
| French female | ff_siwis | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_ff_siwis.mp4?raw=true"></audio> |
|
||||
| Hindi female | hf_alpha | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_hf_alpha.mp4?raw=true"></audio> |
|
||||
| Hindi male | hm_omega | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_hm_omega.mp4?raw=true"></audio> |
|
||||
| Italian female | if_sara | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_if_sara.mp4?raw=true"></audio> |
|
||||
| Italian male | im_nicola | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_im_nicola.mp4?raw=true"></audio> |
|
||||
| Japanese | jf_alpha | <audio controls=""><source type="audio/mp4" src="https://github.com/santinic/audiblez/blob/main/samples/sample_jf_alpha.mp4?raw=true"></audio> |
|
||||
|
||||
## How to install and run
|
||||
|
||||
If you have Python 3 on your computer, you can install it with pip.
|
||||
|
|
@ -30,20 +49,20 @@ sudo apt install ffmpeg espeak-ng libgtk-3-dev # on Ubuntu/Debian 🐧
|
|||
pip install audiblez
|
||||
```
|
||||
|
||||
```python
|
||||
```bash
|
||||
brew install ffmpeg espeak-ng # on Mac 🍏
|
||||
pip install audiblez
|
||||
```
|
||||
|
||||
Then, to run the graphical interface, just type:
|
||||
|
||||
```bash
|
||||
```
|
||||
audiblez-ui
|
||||
```
|
||||
|
||||
If you prefer the command-line instead, you can convert an .epub directly with:
|
||||
|
||||
```bash
|
||||
```
|
||||
audiblez book.epub -v af_sky
|
||||
```
|
||||
|
||||
|
|
@ -56,7 +75,7 @@ It will only produce the `.m4b` file if you have `ffmpeg` installed on your mach
|
|||
|
||||
By default the audio is generated using a normal speed, but you can make it up to twice slower or faster by specifying a speed argument between 0.5 to 2.0:
|
||||
|
||||
```bash
|
||||
```
|
||||
audiblez book.epub -v af_sky -s 1.5
|
||||
```
|
||||
|
||||
|
|
@ -65,17 +84,19 @@ audiblez book.epub -v af_sky -s 1.5
|
|||
Use `-v` option to specify the voice to use. Available voices are listed here.
|
||||
The first letter is the language code and the second is the gender of the speaker e.g. `im_nicola` is an italian male voice.
|
||||
|
||||
| Language | Voices |
|
||||
|----------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| 🇺🇸 | `af_alloy`, `af_aoede`, `af_bella`, `af_heart`, `af_jessica`, `af_kore`, `af_nicole`, `af_nova`, `af_river`, `af_sarah`, `af_sky`, `am_adam`, `am_echo`, `am_eric`, `am_fenrir`, `am_liam`, `am_michael`, `am_onyx`, `am_puck`, `am_santa` |
|
||||
| 🇬🇧 | `bf_alice`, `bf_emma`, `bf_isabella`, `bf_lily`, `bm_daniel`, `bm_fable`, `bm_george`, `bm_lewis` |
|
||||
| 🇪🇸 | `ef_dora`, `em_alex`, `em_santa` |
|
||||
| 🇫🇷 | `ff_siwis` |
|
||||
| 🇮🇳 | `hf_alpha`, `hf_beta`, `hm_omega`, `hm_psi` |
|
||||
| 🇮🇹 | `if_sara`, `im_nicola` |
|
||||
| 🇯🇵 | `jf_alpha`, `jf_gongitsune`, `jf_nezumi`, `jf_tebukuro`, `jm_kumo` |
|
||||
| 🇧🇷 | `pf_dora`, `pm_alex`, `pm_santa` |
|
||||
| 🇨🇳 | `zf_xiaobei`, `zf_xiaoni`, `zf_xiaoxiao`, `zf_xiaoyi`, `zm_yunjian`, `zm_yunxi`, `zm_yunxia`, `zm_yunyang` |
|
||||
| Language | Voices |
|
||||
|---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| 🇺🇸 American English | `af_alloy`, `af_aoede`, `af_bella`, `af_heart`, `af_jessica`, `af_kore`, `af_nicole`, `af_nova`, `af_river`, `af_sarah`, `af_sky`, `am_adam`, `am_echo`, `am_eric`, `am_fenrir`, `am_liam`, `am_michael`, `am_onyx`, `am_puck`, `am_santa` |
|
||||
| 🇬🇧 British English | `bf_alice`, `bf_emma`, `bf_isabella`, `bf_lily`, `bm_daniel`, `bm_fable`, `bm_george`, `bm_lewis` |
|
||||
| 🇪🇸 Spanish | `ef_dora`, `em_alex`, `em_santa` |
|
||||
| 🇫🇷 French | `ff_siwis` |
|
||||
| 🇮🇳 Hindi | `hf_alpha`, `hf_beta`, `hm_omega`, `hm_psi` |
|
||||
| 🇮🇹 Italian | `if_sara`, `im_nicola` |
|
||||
| 🇯🇵 Japanese | `jf_alpha`, `jf_gongitsune`, `jf_nezumi`, `jf_tebukuro`, `jm_kumo` |
|
||||
| 🇧🇷 Brazilian Portuguese | `pf_dora`, `pm_alex`, `pm_santa` |
|
||||
| 🇨🇳 Mandarin Chinese | `zf_xiaobei`, `zf_xiaoni`, `zf_xiaoxiao`, `zf_xiaoyi`, `zm_yunjian`, `zm_yunxi`, `zm_yunxia`, `zm_yunyang` |
|
||||
|
||||
For more detaila about voice quality, check this document: [Kokoro-82M voices](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md)
|
||||
|
||||
## How to run on GPU
|
||||
|
||||
|
|
@ -90,8 +111,8 @@ We don't currently support Apple Silicon, as there is not yet a Kokoro implement
|
|||
Sometimes you want to manually select which chapters/sections in the e-book to read out loud.
|
||||
To do so, you can use `--pick` to interactively choose the chapters to convert (without running the GUI).
|
||||
|
||||
|
||||
## Help page
|
||||
|
||||
For all the options available, you can check the help page `audiblez --help`:
|
||||
|
||||
```
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue