{"version":1,"type":"story","url":"https://digestai.news/story/fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b","json":"https://digestai.news/story/fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b.json","markdown":"https://digestai.news/story/fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b.md","slug":"fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b","headline":"Fish Audio introduces Drama 3 for editing AI voice performances word by word","summary":"Fish Audio launched **Drama 3**, a text-to-speech model designed to let creators adjust AI voice performances with granular control. The tool allows users to change tone, pacing, or emphasis mid-sentence, edit a single word while preserving surrounding audio, and generate multi-speaker scenes with consistent character voices. The company claims this reduces the need to regenerate entire segments when minor adjustments are needed, addressing pain points in audiobook production, dubbed content, and game dialogue creation.\n\nDrama 3’s **audio inpainting** feature lets users select a problematic segment, update instructions, and regenerate only that part while keeping the rest of the performance intact. Fish Audio also highlights multilingual support for English, Chinese, Japanese, and Korean, with phoneme-level pronunciation control. The model is available as a preview via Fish Audio’s API, with an 80% discount on usage for the first 30 days and three free months for qualifying enterprise customers. The company reports over **15 million users** and **$21 million in annual recurring revenue**, positioning Drama 3 as part of its broader speech generation platform.","keyPoints":["Drama 3 lets users edit AI voice performances word-by-word while preserving tone, rhythm, and surrounding audio","Supports multi-speaker scenes with consistent character voices across languages and accents","First 30 days of API usage discounted by 80%, with three free months for qualifying enterprises"],"whyItMatters":"Drama 3 shifts focus from generation to revision, making AI voices more practical for iterative workflows in audiobooks, games, and dubbing. Its word-level editing could reduce wasted time in production, though real-world reliability depends on consistency across voices and languages.","category":{"slug":"marketing","name":"Marketing & Small Business","url":"https://digestai.news/category/marketing"},"entities":{"companies":["Fish Audio"],"models":["Drama 3"],"people":["Rissa Cao","Shijia Liao"]},"firstPublishedAt":"2026-10-13T13:15:43Z","updatedAt":"2026-10-13T13:15:43Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Fish Audio Launches Drama 3 to Direct AI Voices and Edit a Single Word","url":"https://unite.ai/fish-audio-drama-3-ai-voice-direction-audio-inpainting","publishedAt":"2026-10-13T13:15:43Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Fish Audio introduces Drama 3 for editing AI voice performances word by word\", 13 October 2026, https://digestai.news/story/fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b","publisher":"Digest AI","title":"Fish Audio introduces Drama 3 for editing AI voice performances word by word","datePublished":"2026-10-13T13:15:43Z","url":"https://digestai.news/story/fish-audio-introduces-drama-3-for-editing-ai-voice-performances-word-b"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}