VibeVoice

VibeVoice TTS

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

Vpišite se. za 5000 mejnih vrednosti znakov

Za natančen nadzor zavijte svoje besedilo v oznake SSML:

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

Oznake izbranega modela razume – kliknite, da spustite enega v svoje besedilo, kjer se zgodi:

Ta model bere navadno besedilo, zato se v vrstici ignorirajo. Za čustva, ki temeljijo na tag, preklopite na izražen model, kot je Orfeus ali Bark.

Opredelitev posebnih izgovorov (beseda = izgovor):

-12 +12
0.5x 2.0x
Brez Piper, VITS, Melotts
Tukaj se bo pojavil vaš ustvarjeni zvok. Izberite model, vnesite besedilo in kliknite Generiraj.
Uspešno ustvarjen zvok
0:00
Prenesi zvok Prenesi.rt Povezava poteče čez 24h
Brezplačna stopnja: osebna uporaba. Trgovska licenca od 5 $/mo
Ljubi TTS.ai, povej prijateljem!

O projektu 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.

Najboljše za: Podcasts, dialogues, long-form narration, multi-speaker content

Brskaj vse VibeVoice glasovi

Na pogled

Razvijalec
Microsoft
Licenca
MIT
Stopnja
standard
Hitrost
fast
kloniranje glasu
Ne
Jeziki
English, Chinese
Največ znakov
50000

VibeVoice glasovi

Speaker 1

English
Standardno Neutral

Speaker 1 (Chinese)

Chinese
Standardno Neutral

Speaker 2

English
Standardno Neutral

Speaker 2 (Chinese)

Chinese
Standardno Neutral

Speaker 3

English
Standardno Neutral

Speaker 4

English
Standardno Neutral

VibeVoice TTS – Pogosta vprašanja

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.
← Vsi glasovi