HackerTrans
TopNewTrendsCommentsPastAskShowJobs

lharries

no profile record

Submissions

Show HN: Scribe v2 Realtime – new SOTA real-time speech to text model

elevenlabs.io
4 points·by lharries·8 bulan yang lalu·0 comments

How we engineered RAG to be 50% faster

elevenlabs.io
2 points·by lharries·10 bulan yang lalu·0 comments

First Growth Hire

harries.co
1 points·by lharries·tahun lalu·0 comments

How to prompt a conversational AI system

elevenlabs.io
1 points·by lharries·tahun lalu·0 comments

Text to Bark – AI model for communicating with dogs

elevenlabs.io
3 points·by lharries·tahun lalu·2 comments

Show HN: WhatsApp MCP Server

github.com
229 points·by lharries·tahun lalu·138 comments

WhatsApp MCP Server

github.com
1 points·by lharries·tahun lalu·0 comments

Launch and launch again — how to launch your products

harries.co
2 points·by lharries·tahun lalu·0 comments

How do you optimize latency for Conversational AI?

elevenlabs.io
1 points·by lharries·tahun lalu·0 comments

comments

lharries
·tahun lalu·discuss
I used this last week and it's excellent - feels like the same increase in productivity increase from when I first used Cursor.

Are you thinking of doing a hosted version so I can have my team collab on it?

And I found I could open lots of PRs at once but they often need to be dependent on each other - and then I want to make a change to the first one. How are you thinking of better managing that flow?
lharries
·tahun lalu·discuss
Can you choose a voice that's native in that language in the voice library: https://elevenlabs.io/app/voice-library?language=es
lharries
·tahun lalu·discuss
It should work well for the logged in voices here: https://elevenlabs.io/app/voice-library?language=ro

We are in the process of updated the homepage voices for the new languages
lharries
·tahun lalu·discuss
Can you try with this voice? https://elevenlabs.io/app/voice-library?voiceId=xTZlmU8dKXdy...

Voice selection matters more for this model
lharries
·tahun lalu·discuss
Which language isn't good and I'll get that fixed asap?
lharries
·tahun lalu·discuss
There's lots of great german voices here which should be better: https://elevenlabs.io/app/voice-library/collections/SHEPnUB9...

The voice selection matters a lot for this research preview
lharries
·tahun lalu·discuss
If you'd like it to sound like a french person speaking french this voice works great: https://elevenlabs.io/app/voice-library?voiceId=xTZlmU8dKXdy...

Or if you want a french person speaking english with a french accent use that voice with "[French accent]" before it
lharries
·tahun lalu·discuss
If you edit the text so that laugh makes sense in the context it should be much more natural like this one: https://x.com/elevenlabsio/status/1930689782331412811
lharries
·tahun lalu·discuss
can you try with a Romanian voice?
lharries
·tahun lalu·discuss
If you're trying to make an audiobook about an Alabaman visiting Paris this might be quite useful... But in seriousness try it with this voice: https://elevenlabs.io/app/voice-library?voiceId=rbFGGoDXFHtV...
lharries
·tahun lalu·discuss
> The result with OpenAI feels much less predictable and of lower production quality than ElevenLabs

Thank you Ian! Credit to our research team for making this possible

For the prosidy, if you choose an expressive voice the prosidy should be larger
lharries
·tahun lalu·discuss
We have lots of great British voices in our voice library! Or if you want to hear an american trying to do a british accent add "[British accent]" at the start of the generation
lharries
·tahun lalu·discuss
Can you try with a voice that was trained on that language? This research preview is more variable based on the voice chosen
lharries
·tahun lalu·discuss
It's a research preview for now but it should work well in 70+ languages. Voices make a big difference, can you try with a few Russian IVCs?
lharries
·tahun lalu·discuss
One day I hope this can be made for real
lharries
·tahun lalu·discuss
Here at ElevenLabs, we introduced the world's first ultra-realistic Text to Speech model, and recently launched the world's most accurate Speech to Text model, Scribe.

But we're not stopping there.

Today, we're taking one small step for man, and one giant leap for man's best friend.

Introducing Text to Bark, the world's first AI-powered TTS model for dogs.

To use it, just fetch the ElevenLabsClient and then use the model_id Canine v1.

We built it by fine tuning Llama to work with dogs, not just llamas
lharries
·tahun lalu·discuss
Yep!
lharries
·tahun lalu·discuss
For most people, their life isn't stored in neat Notion database.

Instead, if you have calendar + email + their main messaging apps (e.g. WhatsApp) you cover the majority of it. It's messy and unstructured — but luckily LLMs are great at that
lharries
·tahun lalu·discuss
It saves the messages in a local SQLite database on load — so querying shouldn't be an issue as it doesn't contact the WhatsApp server. For sending, this does use the API however and needs more caution
lharries
·tahun lalu·discuss
whatsmeow is in Go. Potentially I could have used a gopy instead and done it all in python (or just done it all in Go)