Changelog

What's new

• Multiple creation modes — Create stories, songs, podcasts, lectures, and quick clips from the same chat-first workflow.
• Richer clip creation — Ask for short audio clips that combine voice, sound effects, and music instead of only single voice lines.
• Research-aware podcasts and lectures — Narra can use research when factual grounding or current information is needed.
• Reusable voice picker — Save designed voices, cloned voices, library voice media, or generated speaker performances to your personal voice picker.
• Improved voice design consistency — Designed voices keep a more stable speaker identity across lines and regenerations while still supporting per-segment emotion.
• Live progress updates — Chat now shows progress for operations like adding segments, updating effects, and regenerating audio.

Demo

Watch the demo video: Brainports AI Audio Studio walkthrough.

What's new

• Conversational story creation — Chat with our AI assistant to develop and refine your stories
• Script-first pipeline — Review and edit your script before generating audio, saving credits and improving quality
• AI voice generation — Preset voices, AI-designed custom voices, and voice cloning from reference audio
• Sound effects — Generate sound effects from text descriptions
• AI music composition — Create instrumental and vocal music with lyrics in 50+ languages
• Audio effects — Phone, radio, walkie-talkie, robotic, child, and elderly voice filters plus spatial panning and reverb
• Timeline editor — Visual waveform editor with drag-and-drop, per-segment editing, and layer mixing
• Media library — Upload, organize, and reuse your voices, sound effects, and music across projects
• Export — Download your final mix as MP3 or WAV with professional loudness normalization
• Subscription plans — Free, Starter, Pro, and Studio tiers with credits and top-ups
• Cookie consent — Granular control over analytics and advertising cookies
• Voice cloning consent — Biometric consent tracking for voice reference uploads
• AI content metadata — All exported audio includes machine-readable metadata identifying it as AI-generated

Improvements

• Real-time generation progress via live status updates
• Cost estimation before audio generation
• Per-segment and per-speaker regeneration
• Non-destructive audio trimming
• Music ducking (auto-lowers music during dialogue)
• Version history for story canvas