VibeVoice

VibeVoice TTS

Microsoft's multi-speaker long-form model that generates up to 90 minutes with 4 distinct speakers.

_Gün tertibi 5000 karakter çäk

Metini SSML taglarda dolap dogry kontrol üçin:

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

Saýlanan model aňlaýan taglar — birini metinde goýmak üçin basyň:

Bu model ýönekeý metin okaýar, şonuň üçin hatda taglar gözden düşürilýär. Tag-based emotions for, switch to an expression model like Orpheus or Bark.

Öz sözleriň terjimesini belli et (söz = terjime):

-12 +12
0.5x 2.0x
Piper, VITS, MeloTTS bilen azat
Siziň döreden audioňyz şu ýerde görüner. Bir model saýlaň, metin girin we döred
Ses mübärek bejerildi
0:00
Ses ýükle .srt ýükle Baglanyşyk 24 sagadyň içinde gutarýar
TTS.ai-ni söýýäňmi? Dostlaryňa aýt!

Habar VibeVoice

VibeVoice from Microsoft is built for long-form, multi-speaker audio. Its 1.5B model can generate up to 90 minutes of speech with as many as 4 simultaneous speakers, using speaker tags to drive multi-turn dialogue — a strong fit for podcasts, audiobooks, and conversations that need speaker consistency across long passages. A separate Realtime 0.5B variant reaches roughly 300ms latency for interactive use. On TTS.ai it covers English and Chinese and accepts up to 50,000 characters per request, so an entire episode can be scripted in one pass.

Muňa iň gowy: Podcasts, dialogues, long-form narration, multi-speaker content

Ehlini _Gözle VibeVoice sesler

Bir seretseň

Developer
Microsoft
Lisenziýa
MIT
_Göçür
standard
Tizlik
fast
Ses klonlamak
_Ýok
Diller
English, Chinese
Maks. karakterler
50000

VibeVoice sesler

Speaker 1

English
_Öň bellenen Neutral

Speaker 1 (Chinese)

Chinese
_Öň bellenen Neutral

Speaker 2

English
_Öň bellenen Neutral

Speaker 2 (Chinese)

Chinese
_Öň bellenen Neutral

Speaker 3

English
_Öň bellenen Neutral

Speaker 4

English
_Öň bellenen Neutral

VibeVoice TTS - Gynançly Soraglar

VibeVoice supports up to 4 distinct speakers and up to 90 minutes of continuous output, with speaker tags for multi-turn dialogue — built for podcasts and long-form narration. It accepts up to 50,000 characters per request.

Yes. Alongside the 1.5B long-form model, a Realtime 0.5B variant achieves roughly 300ms latency for interactive use.

VibeVoice is MIT-licensed. It supports English and Chinese and does not currently support voice cloning.
← Ehli Sesler