Bark logo

Bark

Open-source transformer text-to-audio model by Suno

Bark is a transformer-based text-to-audio model from Suno that generates speech, music, background noise and simple sound effects from text. Its repository describes it as a fully generative text-to-audio model rather than a conventional text-to-speech system. It can also produce nonverbal sounds such as laughing or sighing, triggered by cues like [laughs] or [music] in the prompt. Bark detects the input language automatically and ships with more than 100 speaker presets across 13 languages, English being the best supported. It runs on CPU or GPU through PyTorch and is released under the MIT license. The README says it was developed for research purposes.

Filed under
Audio & Music
Pricing
Free
Platforms
desktop · api
Last updated
November 10, 2026

What Bark does

  • Non-speech sound cues. Prompts can include cues such as [laughs] and [music] to generate nonverbal sounds and music.
  • Automatic language detection. Detects the language of the input text and supports 13 languages including English, German, Hindi and Japanese.
  • Speaker presets. More than 100 speaker presets are included for choosing a voice.
  • CPU or GPU inference. Runs through PyTorch on CPU or GPU, with a small-model option for lower VRAM.
  • MIT license. The code and models are available for commercial use under the MIT license.

Who it’s for

  • Developers experimenting with generative audio models
  • Researchers needing an open-source text-to-audio model
  • Self-hosted speech and sound-effect prototypes

Bark pricing

Free, open source under the MIT license; you supply your own hardware

As listed on November 9, 2026. Check github.com for current prices.

Things to know

  • No custom voice cloning is supported
  • Generated clips run about 13-14 seconds; longer audio needs a separate workflow
  • Full model needs about 12 GB of VRAM; slow on CPU and older GPUs

Quick answers

What is Bark?
Bark is a transformer-based text-to-audio model from Suno that generates speech, music, background noise and simple sound effects from text.
Is Bark free?
Yes. Bark is free to use. (As listed on November 9, 2026.)
Who makes Bark?
Bark is made by Suno and has been available since 2023.
Where can you use Bark?
Bark is available on desktop (apps, editor plugins or browser extensions) and an API for developers.
What are some alternatives to Bark?
Other tools filed in the same section include Whisper, ElevenLabs and Murf AI.

Tags

#text-to-audio#open-source#speech#sound-effects#pytorch

See also

Cross-referenced entries
Upd. today

Whisper

Open-source speech recognition model from OpenAI

speech-recognitiontranscriptiontranslation

desktop · apiFree
Read entry ↗Visit ↗
▲ TrendingEditor’s pickUpd. today

ElevenLabs

AI voice, speech, music and conversational agent platform

text-to-speechvoice-cloningdubbing

web · apiFreemium
Read entry ↗Visit ↗
Upd. today

Murf AI

AI voiceover studio, text-to-speech API and voice agents

voiceovertext-to-speechdubbing

web · apiFreemium
Read entry ↗Visit ↗
Upd. today

Speechify

Text-to-speech reader and voice AI assistant

text-to-speechreaderdictation

web · ios · android · desktop · apiFreemium
Read entry ↗Visit ↗