Today for AI
HOT RADAR
llmHEAT 41.3°

AI CLUSTERED EVENT · 10/14/2026

Fish Audio Open-Sources Drama 3 TTS: Achieving Top Ranking with Word-Level Emotion Redrawing and Bracket-Based Natural Language Control

2 reports archived2 independent sourcesupdated 10/14/2026, 02:55:12
Synthesis & Latest Updates
2 Sources Cross-Validated

Fish Audio has open-sourced its latest text-to-speech model, Drama 3 Preview, which now ranks first on the Artificial Analysis leaderboard due to superior fine-grained emotion control. The model achieves a pronunciation robustness score of 93.2%, significantly outperforming commercial closed-source competitors like Eleven v4 (91.7%) and Turbo, while offering fully open weights for download.

Technically, Drama 3 introduces word-level style redrawing, allowing users to modify tone, speed, or volume for individual words without regenerating entire sentences. This is achieved through bracket-based natural language instructions (e.g., "barely holding on") or paired tags (e.g., Whisper, Slower). With an API pricing of $15 per million characters—far lower than Eleven v4's $80—the model drastically reduces adoption barriers for developers.

This release challenges commercial TTS incumbents by combining high controllability with cost efficiency. It accelerates the deployment of AI voice in complex scenarios such as audiobooks, game NPCs, and virtual streamers, reshaping the competitive landscape of the speech synthesis industry.

LATEST/Drama 3 Preview weights are now available for download on Hugging Face, enabling local deployment or API integration. The community is actively testing multilingual performance, with future updates expected to further optimize long-text stability and emotional coherence.

HEAT TRENDHourly heat curve

4 fully observed hours
Now
41.3
Peak
43.403:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 2 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·78 pts
    • Drama 3 Preview ranks #1 among open-weights models on the Artificial Analysis TTS leaderboard.
    • Achieves 93.2% in Pronunciation Robustness, surpassing Eleven v4 (91.7%) and Eleven v4 Turbo (90.1%).
    • Supports multi-character scenes, long-form content, and natural-language control; weights are open on Hugging Face.
    • API pricing is $15 per million characters, significantly lower than Eleven v4's $80 per million characters.
  2. Rohan Paul (@rohanpaul_ai)T2·68 pts
    • Drama 3 is Fish Audio's latest open-weight TTS model, claiming world-leading emotive expressiveness and controllability.
    • The core innovation is word-level style restyling, allowing users to modify tone, speed, or volume of specific words without regenerating the entire sentence.
    • Control mechanisms include natural language directives within square brackets (multilingual support) and paired modifiers (e.g., Whisper, Forceful), enabling smooth tonal shifts mid-sentence.
Fish Audio Open-Sources Drama 3 TTS: Achieving Top Ranking with Word-Level Emotion Redrawing and Bracket-Based Natural Language Control | Today for AI