Skip to content

Commit

Permalink
GitBook: [#159] rename Mimic 3 slug
Browse files Browse the repository at this point in the history
  • Loading branch information
@gitbook-bot
devops-subscriptions authored and gitbook-bot committed Jun 29, 2022
1 parent 454a79d commit cac0604
Show file tree
Hide file tree
Showing 3 changed files with 25 additions and 25 deletions.
2 changes: 1 addition & 1 deletion docs/SUMMARY.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@
* [Adapt Tutorial](mycroft-technologies/adapt/adapt-tutorial.md)
* [Lingua Franca](mycroft-technologies/lingua-franca.md)
* [Mimic TTS](mycroft-technologies/mimic-tts/README.md)
* [Mimic 3](mycroft-technologies/mimic-tts/coming-soon-mimic-3.md)
* [Mimic 3](mycroft-technologies/mimic-tts/mimic-3.md)
* [Mimic 2](mycroft-technologies/mimic-tts/mimic-2.md)
* [Mimic 1](mycroft-technologies/mimic-overview/README.md)
* [Mimic Recording Studio](mycroft-technologies/mimic-overview/mimic-recording-studio.md)
Expand Down
14 changes: 7 additions & 7 deletions docs/mycroft-technologies/mimic-tts/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,18 +10,18 @@ Over the years, Mimic like other Mycroft components has gotten clearer, faster,

You can hear samples from all three Mimic systems below, speaking the same [sentence](https://clagnut.com/blog/2380/#English\_phonetic\_pangrams).

| Name | Sample | Local | Technology |
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ----- | ----------------------------------------------------------------------------------------------------------- |
| <img src="https://mycroft.ai/wp-content/uploads/2017/02/mimic.png" alt="" data-size="line"> [Mimic 1](../mimic-overview/) | [Mimic 1 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic1\_pangram.wav) | Yes | [Festival Lite (flite)](http://www.festvox.org/flite) |
| <img src="https://mycroft.ai/wp-content/uploads/2019/05/mimic2-logo.svg" alt="" data-size="line"> [Mimic 2](mimic-2.md) | [Mimic 2 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic2\_pangram.wav) | No | [Tacotron](https://github.com/keithito/tacotron) |
| <img src="https://mycroft.ai/wp-content/uploads/2020/10/Mimic_color.png" alt="Mimic logo" data-size="line"> [Mimic 3](coming-soon-mimic-3.md) | [Mimic 3 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic3\_pangram.wav) | Yes | [VITS: Conditional Variational Autoencoder with Adversarial Learning](https://github.com/jaywalnut310/vits) |
| Name | Sample | Local | Technology |
| --------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ----- | ----------------------------------------------------------------------------------------------------------- |
| <img src="https://mycroft.ai/wp-content/uploads/2017/02/mimic.png" alt="" data-size="line"> [Mimic 1](../mimic-overview/) | [Mimic 1 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic1\_pangram.wav) | Yes | [Festival Lite (flite)](http://www.festvox.org/flite) |
| <img src="https://mycroft.ai/wp-content/uploads/2019/05/mimic2-logo.svg" alt="" data-size="line"> [Mimic 2](mimic-2.md) | [Mimic 2 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic2\_pangram.wav) | No | [Tacotron](https://github.com/keithito/tacotron) |
| <img src="https://mycroft.ai/wp-content/uploads/2020/10/Mimic_color.png" alt="Mimic logo" data-size="line"> [Mimic 3](mimic-3.md) | [Mimic 3 sample](https://mycroft.ai/wp-content/uploads/2022/04/mimic3\_pangram.wav) | Yes | [VITS: Conditional Variational Autoencoder with Adversarial Learning](https://github.com/jaywalnut310/vits) |

### COMING SOON: Mimic 3

Mimic 3 is a privacy-focused open-source neural Text to Speech (TTS) engine that can run faster than real-time on low-end devices like the Raspberry Pi 4. In human terms that means it sounds great, it can run completely offline or in the cloud, and you can verifiably trust it.

{% content-ref url="coming-soon-mimic-3.md" %}
[coming-soon-mimic-3.md](coming-soon-mimic-3.md)
{% content-ref url="mimic-3.md" %}
[mimic-3.md](mimic-3.md)
{% endcontent-ref %}

### Mimic 2
Expand Down
34 changes: 17 additions & 17 deletions ...nologies/mimic-tts/coming-soon-mimic-3.md → ...mycroft-technologies/mimic-tts/mimic-3.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,10 @@ description: A fast, privacy-focused, open-source, neural Text to Speech (TTS) e

Mimic 3 is a neural text to speech engine that can run locally, even on low-end hardware like the Raspberry Pi 4. It is the default text to speech engine on the [Mark II](https://mycroft.ai/product/mark-ii/).

* [Install Mimic 3](coming-soon-mimic-3.md#installation)
* [Install Mimic 3](mimic-3.md#installation)
* [Listen to voice samples](https://mycroftai.github.io/mimic3-voices/)
* [See example use cases](coming-soon-mimic-3.md#usage)
* [Learn how it works](coming-soon-mimic-3.md#how-it-works)
* [See example use cases](mimic-3.md#usage)
* [Learn how it works](mimic-3.md#how-it-works)

## Installation

Expand All @@ -20,15 +20,15 @@ Mimic 3 was designed to run on the Raspberry Pi 4 (64-bit OS), but will also run
* `amd64`
* AMD/Intel-based desktops/laptops
* Tested:
* Very fast on Ryzen 9 5950X, [RTF](coming-soon-mimic-3.md#real-time-factor) less than 0.05
* Very fast on Ryzen 9 5950X, [RTF](mimic-3.md#real-time-factor) less than 0.05
* `arm64`
* Raspberry Pi 3/4 and Zero 2 with [64-bit Pi OS](https://www.raspberrypi.com/news/raspberry-pi-os-64-bit/)
* Tested:
* Usable on Pi 4, [RTF](coming-soon-mimic-3.md#real-time-factor) around 0.5
* Usable on Pi 4, [RTF](mimic-3.md#real-time-factor) around 0.5
* `armv7l`
* Raspberry Pi 1/2/3/4 and Zero 2 with 32-bit Pi OS
* Tested:
* Slow on Pi 3, [RTF](coming-soon-mimic-3.md#real-time-factor) around 1.3
* Slow on Pi 3, [RTF](mimic-3.md#real-time-factor) around 1.3

#### Real-Time Factor

Expand Down Expand Up @@ -188,9 +188,9 @@ Once installed, the following commands will be available in `.venv/bin`:

There are many ways to use Mimic 3, including:

* [From the command line](coming-soon-mimic-3.md#command-line-interface)
* [As a web server](coming-soon-mimic-3.md#web-server)
* [In a screen reader](coming-soon-mimic-3.md#speech-dispatcher)
* [From the command line](mimic-3.md#command-line-interface)
* [As a web server](mimic-3.md#web-server)
* [In a screen reader](mimic-3.md#speech-dispatcher)

### Voice Keys

Expand All @@ -200,7 +200,7 @@ Voices in Mimic 3 are keyed by a name with specific parts. These parts include t

The default voice is `en_UK/apope_low`

Voice models are automatically downloaded from [Github](https://github.com/MycroftAI/mimic3-voices) and stored in `${HOME}/.local/share/mycroft/mimic3` (technically `${XDG_DATA_HOME}/mycroft/mimic3`). You can also [manually download them](coming-soon-mimic-3.md#downloading-voices).
Voice models are automatically downloaded from [Github](https://github.com/MycroftAI/mimic3-voices) and stored in `${HOME}/.local/share/mycroft/mimic3` (technically `${XDG_DATA_HOME}/mycroft/mimic3`). You can also [manually download them](mimic-3.md#downloading-voices).

### Command-Line Interface

Expand All @@ -212,7 +212,7 @@ The `mimic3` command can be used to synthesize audio on the command line:
mimic3 --voice <voice> "<text>" > output.wav
```

where `<voice>` is a [voice key](coming-soon-mimic-3.md#voice-keys) like `en_UK/apope_low`. `<TEXT>` may contain multiple sentences, which will be combined in the final output WAV file. These can also be [split into separate WAV files](coming-soon-mimic-3.md#multiple-wav-output).
where `<voice>` is a [voice key](mimic-3.md#voice-keys) like `en_UK/apope_low`. `<TEXT>` may contain multiple sentences, which will be combined in the final output WAV file. These can also be [split into separate WAV files](mimic-3.md#multiple-wav-output).

#### SSML

Expand Down Expand Up @@ -274,7 +274,7 @@ The following SSML tags are supported:
* `lang` - set language for sentence
* `<w>` / `<token>` - word (disables automatic tokenization)
* `<voice name="...">` - set voice of inner text
* `voice` - [voice key](coming-soon-mimic-3.md#voice-keys)
* `voice` - [voice key](mimic-3.md#voice-keys)
* `<prosody attribute="value">` - change speaking attributes
* Supported `attribute` names:
* `volume` - speaking volume
Expand Down Expand Up @@ -431,9 +431,9 @@ See `mimic3-server --help` for more options.
#### Endpoints

* `/api/tts`
* `POST` text or [SSML](coming-soon-mimic-3.md#ssml) and receive WAV audio back
* Use `?voice=` to select a different [voice/speaker](coming-soon-mimic-3.md#voice-keys)
* Set `Content-Type` to `application/ssml+xml` (or use `?ssml=1`) for [SSML](coming-soon-mimic-3.md#ssml) input
* `POST` text or [SSML](mimic-3.md#ssml) and receive WAV audio back
* Use `?voice=` to select a different [voice/speaker](mimic-3.md#voice-keys)
* Set `Content-Type` to `application/ssml+xml` (or use `?ssml=1`) for [SSML](mimic-3.md#ssml) input
* `/api/voices`
* Returns a JSON list of available voices

Expand Down Expand Up @@ -461,13 +461,13 @@ See `mimic3 --help` for more options.

Use the Mimic 3 web server as a drop-in replacement for [MaryTTS](http://mary.dfki.de/), for example with [Home Assistant](https://www.home-assistant.io/integrations/marytts/).

Make sure to use a Mimic 3 [voice key](coming-soon-mimic-3.md#voice-keys) like `en_UK/apope_low` instead of a MaryTTS voice name.
Make sure to use a Mimic 3 [voice key](mimic-3.md#voice-keys) like `en_UK/apope_low` instead of a MaryTTS voice name.

### Speech Dispatcher

Mimic 3 can be used with the [Orca screen reader](https://help.gnome.org/users/orca/stable/) for Linux via [speech-dispatcher](https://github.com/brailcom/speechd).

After [installing Mimic 3](coming-soon-mimic-3.md#installation), start the [web server](coming-soon-mimic-3.md#server). Next, make sure you have `speech-dispatcher` installed:
After [installing Mimic 3](mimic-3.md#installation), start the [web server](mimic-3.md#server). Next, make sure you have `speech-dispatcher` installed:

```
sudo apt-get install speech-dispatcher
Expand Down

0 comments on commit cac0604

Please sign in to comment.