VibeVoice TTS-värden
Microsoft's multi-speaker long-form model that generates up to 90 minutes with 4 distinct speakers.
Radera din text i SSML-taggar för exakt kontroll:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Taggar den valda modellen förstår — klicka för att släppa en i din text där det händer:
Den här modellen läser vanlig text, så inline-taggar ignoreras. För taggbaserade känslor, byt till en uttrycksfull modell som Orpheus eller Bark.
Definiera egna uttal (ord = uttal):
Om jag inte kan 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.
Bäst för: Podcasts, dialogues, long-form narration, multi-speaker content
Bläddra alla VibeVoice rösterMed en blick
- Utvecklare
- Microsoft
- Licens
- MIT
- Nivå
- standard
- Varvtal
- fast
- Röstkloning
- Ej tillämpligt
- Språk
- English, Chinese
- Max tecken
- 50000