Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: VoxConvo – "X but it's only voice messages"

voxconvo.com

Post reply on HN
Print view View original

11–17 of 17 posts

Re: Show HN: VoxConvo – "X but it's only voice messages"

#11

Post by teunlao »

Impressive tech execution, but the format has fundamental scaling issues.

Clubhouse lost 93% of users from peak. WhatsApp sends 7 billion voice messages daily - but those are DMs, not feeds.

The math doesn't work: reading is 50-80% faster than listening. You can skim 50 text posts in 100 seconds. 50 voice posts? 15 minutes.

Voice works async 1-to-1. You built Twitter where every tweet is a 30-second voicemail nobody has time to listen to.

The transcription proves it - users will read, not listen. Which makes this "text feed with worse UX"

Re: Show HN: VoxConvo – "X but it's only voice messages"

#12

Post by estimator7292 »

SrslyJosh wrote: post #8
1bpp wrote: post #3

How would this prevent someone from just plugging ElevenLabs into it? Or the inevitable more realistic voice models? Or just a prerecorded spam message? It's already nearly impossible to tell if some speech is human or not. I do like the idea of recovering the emotional information lost in speech -> text, but I don't think it'd help the LLM issue.

Detecting "human speech" means shutting out people who cannot speak and rely on TTS for verbal communication.

Also speech impediments, accents, physical disabilities, etc etc.

Tech culture just refuses to even be aware of people as physical beings. It's just spherical users in a vacuum and if you don't fit the mold, tough.

Re: Show HN: VoxConvo – "X but it's only voice messages"

#13

Post by siim »

1bpp wrote: post #3

How would this prevent someone from just plugging ElevenLabs into it? Or the inevitable more realistic voice models? Or just a prerecorded spam message? It's already nearly impossible to tell if some speech is human or not. I do like the idea of recovering the emotional information lost in speech -> text, but I don't think it'd help the LLM issue.

True. However making voice input has higher friction than typing chatgpt write me a reply.

Re: Show HN: VoxConvo – "X but it's only voice messages"

#14

Post by siim »

cdrini wrote: post #2

Neat idea! Not sure if I'm willing to register just try it, though. Having the main feed public would be nice! Or even a sample feed.

That's a good call. While there's no general public feed, individual profiles are public. For example, here's mine: https://voxconvo.com/siim

Re: Show HN: VoxConvo – "X but it's only voice messages"

#16

Post by siim »

zahlman wrote: post #7

> I saw this tweet: "Hear me out: X but it's only voice messages (with AI transcriptions)" - and couldn't stop thinking about it. > Why this exists: AI-generated content is drowning social media. > Real-time transcription ... So you want to filter out AI content by requiring users to produce audio (not really any harder for AI than text), and you add AI content afterward (the transcriptions) anyway? I really think yo…

Curious what made you think the backend uses LLMs for content generation?

To clarify:

1. transcription is local VOSK speech-to-text via WebSocket

2. live transcript post-processing has optional Gemini Flash-lite turned on which tries to fix obvious transcription mistakes, nothing else. The real fix here is more accurate transcriber.

3. backend: TypeGraphQL + MongoDB + Redis

The anti-AI stance isn't "zero AI anywhere", it's about requiring human input.

AI-generated audio is either too bad or too perfect. Real recorded voice has human imperfections.

Re: Show HN: VoxConvo – "X but it's only voice messages"

#17

Post by siim »

teunlao wrote: post #11

Impressive tech execution, but the format has fundamental scaling issues. Clubhouse lost 93% of users from peak. WhatsApp sends 7 billion voice messages daily - but those are DMs, not feeds. The math doesn't work: reading is 50-80% faster than listening. You can skim 50 text posts in 100 seconds. 50 voice posts? 15 minutes. Voice works async 1-to-1. You built Twitter where every tweet is a 30-second voicemail nobody…

Speaking > typing for creation.

Reading > listening for consumption.

Talk to create, read to consume.

Post reply on HN