Drama 3 now available on AI Gateway
By Steven Van ·
The preview text-to-speech model is 80% off through November 12 and supports script-based voice direction and multi-speaker dialogue.
Fish Audio’s Drama 3 is 80% off through November 12 on Vercel’s AI Gateway. The text-to-speech model is currently in preview for uses including voiceovers, character dialogue, and audio storytelling.
Direct performances within the script
Scripts can include natural-language directions in square brackets to control emotion and pacing, along with sounds and pauses. Whisper or emphasis tags change the delivery of selected words. Directions can be written in a different language from the spoken text.
Drama 3 also supports multi-speaker dialogue, with a separate voice for each character.
Try the model
Use the model name fish-audio/drama-3 to get started, or try it in the model playground. The release note includes an AI SDK example that generates speech and saves it as an MP3.