Bark
Text-to-audio model supporting speech, music, and sound effects
Voice & AudioFree (open-source)★ 36,000Works with OpenClaw
About Bark
Bark by Suno is an open-source text-to-audio model that generates speech, music, and sound effects. It supports multiple languages, speaker presets, and can produce non-verbal sounds like laughter and sighing.
Features
Text-to-speech
Music generation
Sound effects
Multi-language
Voice presets
The tally
FOR
- +Speech + music + sound effects
- +Multi-language support
- +Speaker presets
- +Open-source
- +Unique capabilities
AGAINST
- −Slower than ElevenLabs
- −Lower quality than commercial TTS
- −Requires GPU
- −No real-time streaming
Related concepts
Kept nearby
Resemble AI
Voice cloning with deepfake detection built in
From $29/mo
ElevenLabs
AI voice synthesis and cloning platform
Free + from $6/mo
Descript
Edit audio and video by editing the transcript
Free + from $16/mo
Cartesia
Ultra-low-latency realtime voice AI (Sonic)
Free tier + usage-based
Browse all Voice & Audio tools →