DramaBox by Resemble AI
DramaBox is an open-source TTS model that turns natural language scene descriptions into expressive vocal performances, with every output watermarked for provenance. It supports 48kHz stereo broadcast-quality audio and requires no style tags or post-processing. Currently English-only.
The complete generative AI security platform | Resemble AI | Product Hunt
The complete generative AI security platform
570 followers
The complete generative AI security platform
570 followers
Visit website
Text-to-Speech Software
Deepfakes are everywhere. So are we. Resemble AI secures enterprise generative AI from creation through distribution. We build foundational voice models used across industries from entertainment to government, watermark multimodal outputs with imperceptible marks, and detect AI-generated audio, image, and video at production scale. Trusted by Deutsche Telekom, Netflix, Telnyx, and Paramount, on-prem and in the cloud.
Overview
Launches8
Reviews
Alternatives
Built with
Team
Awards
More
This is the 8th launch from Resemble AI. View more
DramaBox by Resemble AI
Launching today
AI turns scene descriptions into vocal performances
A TTS model should give you two things: an oscar-worthy performance and a verifiable signature to prove it's yours. DramaBox is the first to do both. Describe a scene the way you would to an actor, like 'a talk show host gasps in mock shock, bursts into laughter,' and the model interprets it as performance. Every output is watermarked with Resemble Watermarker. Open source, English-only for now, find it in your Resemble account or on Hugging Face.
Free
Launch tags:Productivity•Artificial Intelligence•GitHub
Launch Team / Built With
Subscribe
SocialLinkedInX
Previous Resemble AI Launches
Chatterbox TurboFast, expressive, open source TTS with native watermarking
Launched on December 30th, 2025
Edit By Resemble AIEdit your audio, just like you edit a typo in your document
Launched on September 17th, 2024
Speech-to-SpeechUse your voice to create realistic AI speech in real-time
Launched on September 22nd, 2022
MyValentine AISend your loved ones an AI generated Valentines day message
Launched on February 14th, 2022
View all Resemble AI launches
Reviews
Most Informative
No reviews yetBe the first to leave a review for Resemble AI
Build agents & automations integrated across your workspace
Promoted
Maker
📌
Hey Product Hunt 👋 Tedi here, CTO at Resemble AI.
Today we're launching DramaBox, a watermarked and open-source TTS model you direct the way you'd direct an actor.
What you put in:
- A natural language scene description
- Dialogue in quotes (e.g., "HAHAHA! I can't believe it!")
- Optional: a reference voice that the model will clone from, or let the model pick one that fits the scene
- Example: 'A talk show host gasps with shock, "No! You did NOT just say that!" He bursts into uncontrollable laughter, "Hahaha! Oh my god, oh my god!" He wheezes, "I cannot, I literally cannot breathe right now!"'
What you get out:
- An expressive vocal performance with laughter, gasps, pacing, and emphasis driven by the scene description
- 48kHz stereo, broadcast-quality output
- A single audio file ready to ship
- PerTh watermarking embedded at generation for provenance
All without style tags, emotion tags or post-processing required! DramaBox is open source, and available on GitHub, Hugging Face or in your Resemble account.
A note on why we included watermarking by default: gen AI is being used in increasingly malicious ways, so voice AI with embedded security gives everyone who builds with DramaBox a verification advantage. If you're building an agent, feel free to check out our detection API as well.
Curious to see and hear what you build, please share feedback or any interesting edge cases with us here.
Tedi
Report
11h ago
The shift from text to vocal performance is exciting for storytellers. Is there support for multiple characters with distinct accents within a single scene description?
Report
12m ago