Bark TTS

Runs TTS with Bark.

Try it in the Widget Center

Click this url to try this widget and copy the Pro Config template.

Usage

Supported Languages

  • English

  • Chinese

  • German

  • Spanish

  • French

  • Hindi

  • Italian

  • Japanese

  • Korean

  • Polish

  • Portuguese

  • Russian

  • Turkish

The languages are auto-detected. Bark-TTS also supports serval non-speech sounds.

Input Parameters

Name
Type
Description
Default
Required

prompt

string

The text prompt for model to generate audio. Here are some non-speech sounds:

                                    - [laughter]
                                    - [laughs]
                                    - [sighs]
                                    - [music]
                                    - [gasps]
                                    - [clears throat] 
                                    - — or ... |  for hesitations
                                    - ♪  | for song lyrics
                                    - Capitalization | for emphasis of a word
                                    - NARRATOR: / MAN: / WOMAN: | for bias towards speaker</td><td>Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.</td><td>false</td></tr>

Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.

history_prompt

string

history choice for audio cloning, choose from the list. To mitigate misuse of this technology, we limit the audio history prompts to a limited set.

                                    It is possible to use for example a german history prompt with english text. This usually leads to english audio with a german accent.</td><td>en_speaker_0</td><td>false</td></tr>

en_speaker_0

text_temp

number

generation temperature during text encoding (1.0 more diverse, 0.0 more conservative)

0.7

waveform_temp

number

generation temperature during wavform generation (1.0 more diverse, 0.0 more conservative)

0.7

Output Parameters

Name
Type
Description
File Type

url

string

The audio that was generated has been saved as an online URL. This link is temporary, so please save it for your own use

audio

Output Example

{
  "url": "https://cdn.myshell.ai/audio/chat/embed_obj/38145/20240423/fa7e6014529f41c1aa747f765f00c385.mp3"
}
PreviousWidgetsNextChamp

Last updated