November 2026 Summaries

Fish Audio has introduced Live 3, a full-duplex English voice model designed to listen while speaking and adapt to natural conversational behaviors such as pauses, acknowledgments, interruptions, and mid-sentence changes of mind. Rather than relying primarily on rule-based thresholds across separate speech recognition, reasoning, synthesis, and turn-taking components, Live 3 incorporates conversational timing into its speech model through training on real human conversations. It can respond in as little as 186 milliseconds with brief acknowledgments while leaving room for callers to continue, distinguish backchannel responses like “yeah” from actual interruptions, and pause while users revise requests such as orders or bookings. Fish Audio positions the model for uses including support calls, reservations, and ordering systems, and says it is available through the Fish Agent Platform, API, and on-premises enterprise deployments.

Fish Audio Story Studio is a long-form AI audio editor designed for creating multi-voice audiobooks, documentaries, meditations, podcasts, and audio dramas from written scripts. Users can begin with a blank project, import Word, PDF, or text manuscripts that the system splits into chapters and speakers, or explore templates, then generate speech paragraph by paragraph as editable blocks. The platform supports character-specific voices, including official licensed options and cloned voices, emotion tags, configurable delays, speech-model selection, volume and speed controls, text and loudness normalization, and saved generation histories for comparing alternate takes. Its timeline enables users to adjust pacing, reposition clips, add imported music or sound effects, and synchronize visual pauses with script markers, while chapter controls and project settings help organize longer productions and establish default voices, models, and mixing behavior. Audio generation and previews are available to all users, but downloading blocks or exporting projects requires a paid plan; exports can include selected chapters, single or segmented MP3 or WAV files, and optional SRT subtitles, with additional credits needed only for blocks that have not yet been generated.