Narration Room
Turn source text into editable multi-voice scripts
70 followers
Turn source text into editable multi-voice scripts
70 followers
Narration Room is a native Mac app, not just a text-to-speech box. It turns source text into editable multi-voice scripts, then lets creators cast voices, adjust delivery, preview on a visual timeline, and export polished audio. Standouts: source-grounded AI modes, 40+ on-device voices, PDF/Word/Markdown import, dictation mode; offline and local.
Narration Room
The "source text to spoken script to AI audio" pipeline is something I'd genuinely use. I run a podcast on financial modeling (ModeLoop Podcast on Spotify) and the unglamorous reality is that turning written research into something that sounds natural out loud is most of the work. A multi-voice script editor that handles that transform in one place could cut my prep time a lot. Does it hold up for longer-form, dialogue-style episodes, or is it best for shorter narration?
Narration Room
@samir_asadov thank you for the feedback. That was exactly the use case that compelled me to create Narration Room. Yes it does hold up for longer-form and dialogue-style episodes, there are 3 AI assisted script drafting options
@schmittsfn that's great to hear — the dialogue hold-up is the real test, since multi-voice pacing is where most TTS workflows fall apart. The 3 script-drafting options are the smart part too; scripting is usually the actual bottleneck, not the voice. Tightening dialogue pacing on longer ModeLoop Podcast episodes is exactly what I'd want to streamline, so I'll give Narration Room a proper run on a full-length one and report back.
The multi-voice script + visual timeline approach is what sets this apart from the usual TTS box — casting different voices and tweaking emphasis/pitch before export is basically how I'd build a vocal arrangement. What export formats do you support? Would love clean WAV out so I could drop the narration straight into my DAW. Love that it's all on-device too.
Narration Room
@lennoxbeflying supporting SSML for more fine grained control is only the beginning, another feature that could be very useful is to "formalize" natural language instructions somehow so that you can edit and tweak the audio without having to describe it--more of a convenience feature
Narration Room supports .wav, .m4a and .mp3
Great launch Stefan! Turning source text into editable multi-voice scripts is such a creative tool for podcast and audiobook creators. Does Narration Room support voice cloning or custom voice profiles, or is it working with a set of pre-built narrator voices?
Narration Room
@dannyheng thank you for the feedback! Right now you have a large selection of pre-defined narrator voices, but voice cloning is part of the pipeline of planned features
The offline and local-first approach is what stands out to me. Feels like a refreshing change from everything being cloud-based these days.
Narration Room
@workout097_collab thank you, Vasyl. On-device and privacy is very important to us and we‘ll strive to provide more voices and naturalness in the future