mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
docs: clarify paralinguistic tag support in quick start (#450)
Co-authored-by: txhno <[email protected]>
This commit is contained in:
@@ -105,7 +105,12 @@ Five TTS engines with different strengths, switchable per-generation:
|
||||
|
||||
### Emotions & Paralinguistic Tags
|
||||
|
||||
Type `/` in the text input to insert expressive tags that the model synthesizes inline with speech (Chatterbox Turbo):
|
||||
Only **Chatterbox Turbo** interprets paralinguistic tags like `[laugh]` and
|
||||
`[sigh]`. Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and HumeAI TADA read them
|
||||
literally as text.
|
||||
|
||||
With **Chatterbox Turbo** selected, type `/` in the text input to open the tag
|
||||
inserter and add expressive tags inline with speech:
|
||||
|
||||
`[laugh]` `[chuckle]` `[gasp]` `[cough]` `[sigh]` `[groan]` `[sniff]` `[shush]` `[clear throat]`
|
||||
|
||||
|
||||
@@ -69,6 +69,16 @@ Now let's use your new voice profile to generate speech.
|
||||
```
|
||||
Hello! This is my first voice generation with Voicebox.
|
||||
```
|
||||
|
||||
<Callout type="info">
|
||||
Paralinguistic tags like `[laugh]`, `[sigh]`, and `[gasp]` only work with
|
||||
**Chatterbox Turbo**. Qwen3-TTS, LuxTTS, Chatterbox Multilingual, and
|
||||
HumeAI TADA will read those tags literally instead of turning them into
|
||||
expressive sounds.
|
||||
</Callout>
|
||||
|
||||
To insert supported tags, select **Chatterbox Turbo** and type `/` in the
|
||||
text input to open the tag inserter.
|
||||
</Step>
|
||||
|
||||
<Step title="Generate">
|
||||
|
||||
Reference in New Issue
Block a user