63
Stack Score
Editorial pick✓ Verified working
Bark by Suno
Open-source generative TTS with non-speech sounds.
Try Bark by Suno✓ Free trial available
Best for
Researchers and tinkerers who want expressive TTS with non-speech sounds (laughter, music cues).
At a glance
- Pricing
- free
- Setup time
- 20 minutes
- Learning curve
- moderate
- Last verified
- 5/22/2026
What we love
- ✓Most expressive open TTS
- ✓Fun non-speech features
- ✓Permissive license
Where it falls short
- −Unpredictable outputs
- −No voice cloning out of the box
- −Stale — Suno moved on to music
Pricing
✓ Pricing verified Jun 21, 20261 tier
Open Source
$0
forever
- ✓All weights
- ✓Self-host
- ✓MIT license
Why we picked it
Bark is uncanny — laughter, sighs, [music] tags. Closed-source successor is Suno's audio. The OG open model is still a great toy and a real research baseline.
Overview
Open-source generative TTS with non-speech sounds. Researchers and tinkerers who want expressive TTS with non-speech sounds (laughter, music cues).
Key features
- ●Generative TTS with non-speech tokens
- ●100+ speaker presets
- ●13 languages
- ●Singing and music gen (limited)
- ●MIT licensed
- ●Local PyTorch
- ●Active forks
Best use cases
Expressive narration
Audiobooks where sighs and pauses matter.
TTS research baseline
Reference point for generative speech work.
Integrations
Similar tools
See all voice & audio tools →One AI Stack pick every week.
The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.