Dia TTS TTS
A 1.6B-parameter model purpose-built for generating natural multi-speaker dialogue, not just single-voice narration.
Wrap your text in SSML tags for precise control:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags déi d'gewielt Modell verstinn - klickt fir eng an Ärem Text ze setzen wou se geschitt:
Dëse Modell liest einfache Text, sou datt Inline-Tags ignoréiert ginn. Fir Tag-baséiert Emotiounen, wielt e expressiven Modell wéi Orpheus oder Bark.
Eegen Aussproochen definéieren (Wuert = Aussprooch):
Iwwer Dia TTS
Dia by Nari Labs is a 1.6-billion-parameter text-to-speech model designed from the ground up for dialogue rather than monologue. It generates conversations between two speakers with realistic turn-taking, prosody, and emotional expression, producing audio that sounds like a real exchange instead of two voices read separately. Architecturally it pairs an autoregressive transformer with the Descript Audio Codec (DAC) for waveform generation. Dia is a strong fit for podcast-style content, scripted audiobook dialogue, and conversational scenes, and is released under Apache 2.0. Generations are heavier than single-voice models, so it favors quality over raw speed.
Bescht fir: Podcasts, audiobook dialogues, conversational content
All sichen Dia TTS StimmenOp ee Bléck
- Entwéckler
- Nari Labs
- Lizenz
- Apache 2.0
- Tier
- standard
- Geschwindegkeet
- medium
- Sprooche-Klonen
- Nee
- Sproochen
- English
- Maximal Zeichen
- 800