Bark

Permissive

Suno · Bark · Released 2023-04

~1B (combined sub-models)Audio

A fully generative text-to-audio model that can produce speech, music, and sound effects, but with less voice-cloning control than dedicated TTS models.

Strengths

  • +MIT license, unrestricted use
  • +Can generate non-speech sounds, music, and expressive tone alongside speech
  • +No text-alignment/phoneme pipeline required

Limitations

  • -Less reliable voice consistency/cloning than XTTS-style models
  • -Slower and less predictable than dedicated TTS architectures

License

MIT

use commercially with attribution niceties

Hardware

runs on a good consumer GPU (or Apple Silicon) with quantization

Links

Stats

suno/bark— downloads·— likes

via Hugging Face

Related models