VocalVia

Turn documents and articles into editable multi-voice audio

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉

Zoey, my saved reading pile has quietly turned into a graveyard, so the thought of finally hearing all of it while I walk the dog feels like a small relief. This is the first time that promise has not made me wince.

How does it know when to omit or alter details for spoken format compared to keeping them as is, particularly when referring to technical aspects such as reference, numbers, or technical jargon that requires accuracy?

Editable script before audio is the right call — most TTS tools skip exactly that step. My question is about fiction: in a novel excerpt the speaker is usually implied, not tagged ("she said" disappears after the first exchange). Does the outline step attempt dialogue attribution so characters land on distinct voices, or is fiction a manual-reassignment job today? That feels like the gap between "documents" and "books."

this is one of the more thoughtful takes on document-to-audio I've seen, mostly because the editable script step exists at all instead of piping straight to TTS. one thing I didn't see covered yet: pronunciation of jargon, acronyms, and author names in research papers. that's usually where TTS breaks the listening experience even when the sentence structure is fine - a mispronounced term every few minutes pulls you right out of it. is there a way to correct or lock in a pronunciation once, so it applies consistently across the rest of that document (or future ones with the same terms)?

I believe that editing the script will take time. If I have to review the content anyway, I might just read the PDF instead. Were there users that could relate to my feedback ?

The editable-per-segment part is what stands out to me over plain TTS — being able to refine one speaker's line without re-rendering the whole thing is the tedious bit everywhere else. Turning a research paper into a two-host format is a genuinely nice use case. How much control do you get over pacing and emphasis within a segment, or is picking the voice the main lever right now?

Multi-voice from a single document is a nice unlock — script studios usually make you assign voices manually shot by shot. How are you handling voice consistency across a long document, especially if the same "character" voice needs to reappear later? That's been one of the trickier problems building voice tooling alongside video generation.

@Zoey Congrats on the launch of VocalVia! 🚀 Solving the "saved articles I never actually read" problem by turning them into editable multi-voice podcasts is brilliant.

Quick question on handling complex structures: when processing dense documents (like 30+ page research papers with heavy inline citations, tables, or math code), how clean is the initial script translation? Does it automatically distill complex tables into natural conversation, or do you find users usually need to manually edit those segments first?

The multi-voice output caught me off guard, it actually feels like a real conversation instead of that robotic single narrator you get elsewhere. Refining one segment without regenerating the whole file is a lifesaver for long papers.

Dropped a 40-page research paper in and got a pretty clean two-host audio rundown in a few minutes. Editing individual segments before export is a nice touch, especially for cleaning up citations.

Hey! Editable scripts before audio generation is the part most TTS tools skip, and it's the part that matters. Does it keep speaker assignments stable when you re-edit a segment, or does the outline regenerate?

A timeline or chapter marker system would be really useful so I can jump back to a specific section in long papers without rewinding through the whole audio.

Finally tried it on a 40-page research paper and the multi-voice narration actually makes the dense sections easier to follow than my usual text-to-speech. Editing individual segments before export is a nice touch too.

The multi-voice part caught my eye. When VocalVia turns a document or article into audio, how much control does the user get over which sections use which voice? For example, can someone mark quotes, headings, or different speakers before generation, or is that handled automatically? Since the tagline mentions editable audio, I’m also curious whether edits happen at the text level, the timeline level, or both.