Drama 3
Drama 3 is an AI text-to-speech model from Fish Audio that allows users to direct voice performances by adding natural-language instructions, sounds, emotions, pacing, whispers, laughter, and pauses even within single sentences. It supports multi-character scenes and 83 languages, accessible via web, mobile, and API with open-source weights under a community license.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 18, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 34 out of 100, Poor
- Accessibility
- 92 out of 100, Good
- Best Practices
- 96 out of 100, Good
- SEO
- 100 out of 100, Good
Website checks are queued. Results will appear here when complete.
Around the Web
I've used Fish Audio for their text to speech feature, and i find that most of the audio features found in the library are pretty good. You can find multiple types of voices for the task you wish to accomplish with it, or just use it for fun or more personal projects.
antonio_bud · Review on Product Hunt
We evaluated a lot of TTS providers before making Fish Audio the default in InsForge’s model gateway. It came down to quality, speed, and reliability — and Fish Audio checked all three. Now we’re running it across 15,000+ developers and over 1B tokens/month, and it’s been rock solid. The thing that stands out most is the model quality — you can tell there’s real research depth behind it. And the team ships fast and stays close to partners, which matters a lot when we’re scaling.
hanghuang · Review on Product Hunt
Giving Fish a try vs. other speech apps (11Labs, HeyGen, etc.). Should the tags work on the demo version? Read your doc, but they do not seem to work when I generate a file. The cloning was quite good, even in the demo version, which has some limitations.
cdllc_1 · Review on Product Hunt
I saw the uncle roger ad before seeing the launch here. I don't know what is SOTA but voice cloning took like half a minute! That's incredible (and a little scary!)
christianruink · Imported from Product Hunt
Controlling a pause or an emotion change inside one sentence feels much closer to directing a performance. That's the level where a line can be technically correct and still sound wrong.
oleksii_sekundant · Imported from Product Hunt