Skip to content
AImpact
IT EN
Medium Voice & Audio · 1 min read

Bark: open source TTS with laughter, sighs, and music from text

In one sentence Suno AI releases Bark on HuggingFace: an open source TTS model capable of generating paralinguistics — laughter, sighs, sound effects, music — directly from text prompts.

Verified Official source
ShareLinkedInX
Reading level

Traditional TTS models generate voice but not expression: they speak flatly, without laughter, nervous pauses, or emotional tone changes. Bark breaks this pattern by bringing paralinguistics to open source TTS.

By passing text with special tags like "[laughs]" or "[sighs]", Bark generates audio that truly includes those vocal expressions. But it doesn't stop there: it can also generate musical fragments and ambient sound effects mixed with speech.

The model is released on HuggingFace with open source weights, making it immediately available to the community and opening new possibilities for audiobooks, video games, and multimedia content.

Companies

Suno AI

Tools

Bark

Tags

BarkSuno AITTSParalinguisticsOpen SourceHuggingFaceAudio Generation

Sources