Skip to content

Drama 3 now available on AI Gateway

,

Drama 3, Fish Audio’s text-to-speech model, is now available in preview on AI Gateway and 80% off through November 12.

Use it for voiceovers, character dialogue, and audio storytelling, with:

  • Voice controls: Set emotion and pacing with instructions in square brackets, add sounds and pauses, or apply tags such as <whisper> and <emphasis> to selected words.

  • Multilingual directions: Write instructions in a different language from the spoken text.

  • Multi-speaker dialogue: Assign a separate voice to each character.

Use fish-audio/drama-3 with the AI SDK:

import { experimental_generateSpeech as generateSpeech } from 'ai';
import { writeFile } from 'node:fs/promises';


const result = await generateSpeech({
  model: 'fish-audio/drama-3',
  text: '[warm and reassuring] Take your time. <whisper>I am right here.</whisper>',
  voice: 'f3a2b90078d54a65af4b95f63bc7798e',
  outputFormat: 'mp3',
});


await writeFile('speech.mp3', result.audio.uint8Array);

Generate an MP3 with emotion and whisper instructions.

Choose a voice from Fish Audio’s voice library and use its ID as voice. For authentication and setup, follow the speech quickstart.

Try Drama 3 in the model playground.