Bark

Bark TTS

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

Užsiregistruoti 5000 ženklų riba

Apvynioti savo tekstą BSML žymės tiksliam valdymui:

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

Žymos pasirinktas modelis supranta — spustelėkite, kad įmestų vieną į tekstą, kur tai atsitinka:

Šis modelis skaito paprastą tekstą, todėl į eilę orientuotos žymės yra ignoruojamos. Dėl įsagų pagrindu išreikštos emocijos pereikite prie tokio išraiškingo modelio kaip Orpheus arba Bark.

Apibrėžti užsakymą tarimas (žodžio = tarimas):

-12 +12
0.5x 2.0x
Laisvas su piper, VITS, meloTTS
Čia bus rodomas Jūsų sugeneruotas garsas. Pasirinkite modelį, įveskite tekstą ir spustelėkite Generuoti.
Garsas sėkmingai generuojamas
0:00
Atsiųsti garsą Atsisiųsti.srt Sąsaja baigiasi 24 val.
Laisvas lygis: asmeninis naudojimas. Komercinė licencija iš $5/mo
Mėgstu TTS.ai? Papasakok draugams!

Apie 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.

Geriausia: Creative audio content, audiobooks with emotion, sound effects

Naršyti viską Bark balsai

Iš pirmo žvilgsnio

Programuotojas
Suno
Licencija
MIT
Pakopa
standard
Greitis
slow
Balso klonavimas
Nr.
Kalbos
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Daugiausia simbolių
200

Bark balsai

Chinese Speaker 1

Chinese
Standartinis Neutral

Chinese Speaker 2

Chinese
Standartinis Neutral

English Female 1

English
Standartinis Female

English Female 2

English
Standartinis Female

English Female 3

English
Standartinis Female

English Female 4

English
Standartinis Female

English Male 1

English
Standartinis Male

English Male 2

English
Standartinis Male

English Male 3

English
Standartinis Male

English Male 4

English
Standartinis Male

English Male 5

English
Standartinis Male

English Male 6

English
Standartinis Male

French Speaker 1

French
Standartinis Neutral

French Speaker 2

French
Standartinis Neutral

German Speaker 1

German
Standartinis Neutral

German Speaker 2

German
Standartinis Neutral

Hindi Speaker 1

Hindi
Standartinis Neutral

Italian Speaker 1

Italian
Standartinis Neutral

Japanese Speaker 1

Japanese
Standartinis Neutral

Japanese Speaker 2

Japanese
Standartinis Neutral

Korean Speaker 1

Korean
Standartinis Neutral

Korean Speaker 2

Korean
Standartinis Neutral

Polish Speaker 1

Polish
Standartinis Neutral

Portuguese Speaker 1

Portuguese
Standartinis Neutral

Russian Speaker 1

Russian
Standartinis Neutral

Spanish Speaker 1

Spanish
Standartinis Neutral

Spanish Speaker 2

Spanish
Standartinis Neutral

Turkish Speaker 1

Turkish
Standartinis Neutral

Bark TTS – DUK

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.
← Visi balsai