Bark

Bark TTS

Suno's transformer-based text-to-audio model that generates speech plus laughter, sighs, music, and sound effects.

Sign up for 5,000 character limit

Wrap your text in SSML tags for precise control:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Tags the selected model understands — click to drop one into your text where it happens:

This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free with Piper, VITS, MeloTTS
Your generated audio will appear here. Choose a model, enter text, and click Generate.
Audio Generated Successfully
0:00
Download Audio Download .srt Link expires in 24h
Free tier: personal use. Commercial license from $5/mo
Love TTS.ai? Tell your friends!

About Bark

Bark comes from Suno and takes a different approach from most TTS systems: it is a GPT-style transformer trained as a text-to-audio model rather than a pure text-to-speech one. Because it generates raw audio tokens, it can produce nonverbal sounds — laughing, sighing, crying — as well as background music and sound effects alongside the spoken words. It ships with 100+ speaker presets and handles 13+ languages including English, Chinese, French, German, Hindi, Japanese, and Korean. The trade-off is speed and length: at 350M parameters it runs slowly (~15s per clip) and caps at 200 characters, so it shines for short, emotive, creative audio rather than long narration.

Best for: Creative audio content, audiobooks with emotion, sound effects

Browse all Bark voices

At a glance

Developer
Suno
License
MIT
Tier
standard
Speed
slow
Voice cloning
No
Languages
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Max characters
200

Bark voices

Chinese Speaker 1

Chinese
Standard Neutral

Chinese Speaker 2

Chinese
Standard Neutral

English Female 1

English
Standard Female

English Female 2

English
Standard Female

English Female 3

English
Standard Female

English Female 4

English
Standard Female

English Male 1

English
Standard Male

English Male 2

English
Standard Male

English Male 3

English
Standard Male

English Male 4

English
Standard Male

English Male 5

English
Standard Male

English Male 6

English
Standard Male

French Speaker 1

French
Standard Neutral

French Speaker 2

French
Standard Neutral

German Speaker 1

German
Standard Neutral

German Speaker 2

German
Standard Neutral

Hindi Speaker 1

Hindi
Standard Neutral

Italian Speaker 1

Italian
Standard Neutral

Japanese Speaker 1

Japanese
Standard Neutral

Japanese Speaker 2

Japanese
Standard Neutral

Korean Speaker 1

Korean
Standard Neutral

Korean Speaker 2

Korean
Standard Neutral

Polish Speaker 1

Polish
Standard Neutral

Portuguese Speaker 1

Portuguese
Standard Neutral

Russian Speaker 1

Russian
Standard Neutral

Spanish Speaker 1

Spanish
Standard Neutral

Spanish Speaker 2

Spanish
Standard Neutral

Turkish Speaker 1

Turkish
Standard Neutral

Bark TTS — FAQ

Yes. Bark is a text-to-audio model, so beyond speech it can generate nonverbal cues like laughing, sighing and crying, plus music and background sound effects — one of its defining capabilities.

Yes. Bark is MIT-licensed, which permits commercial use.

Bark caps at 200 characters per request and is on the slower side (around 15 seconds per clip), so it is best suited to short, expressive snippets rather than long-form audio. It does not support voice cloning.
← All voices