Bark
SunoAudio & Speech
78.0
Performance
★ 4.0
Rating
420
Reviews
Text-to-SpeechMusic GenerationOpen Source
About
Suno's open-source text-to-audio model capable of generating speech, music snippets, and sound effects from text prompts.
Strengths
Versatile open-source model generating speech, music, and sound effects from text. Multilingual speech synthesis. Can generate nonverbal sounds like laughter, sighs, and music cues. Fully open-source for local deployment.
Specifications
- Context window
- —
- Parameters
- —
Available On
HuggingFaceGitHubReplicateLocal deployment
Features
text to speechmusic generationsound effectsmultilingual
Performance Trend
Benchmark score trends over time for the top 5 benchmarks.
Loading history...
Benchmarks
Scores from various benchmark tests; higher is better.
| Test | Score | Percentile | Source |
|---|---|---|---|
| MOS | 76.0 | p72 | seed |
