VibeVoice TTS
Microsoft's multi-speaker long-form model that generates up to 90 minutes with 4 distinct speakers.
Bungkus teks Anda dalam tag SSML untuk kendali yang tepat:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tag yang dipilih mengerti klik °C untuk memasukkan satu ke dalam teks Anda di mana hal itu terjadi:
Model ini membaca teks biasa, sehingga tag inline diabaikan. Untuk tag berbasis emosi, beralih ke model ekspresif seperti Orpheus atau Bark.
Definisikan pengucapan ubahan (kata = pelafalan):
Tentang 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.
Terbaik untuk: Podcasts, dialogues, long-form narration, multi-speaker content
Jelajahi semua VibeVoice suaraPada sekilas
- Pengembang
- Microsoft
- Lisensi
- MIT
- Tier
- standard
- Kecepatan
- fast
- Penklonan Suara
- Tidak
- Bahasa
- English, Chinese
- Karakter maksimal
- 50000