Hey all,
Almost as impressive as all the LLMs these days is the voice that ChatGPT uses with its emphasis and dramatic pauses and umms, etc.
I would love to integrate that with a self-hosted Llama3 engine.
Is there a project that y’all have heard of?
A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don’t control.
Rules:
Be civil: we’re here to support and learn from one another. Insults won’t be tolerated. Flame wars are frowned upon.
No spam posting.
Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it’s not obvious why your post topic revolves around selfhosting, please include details to make it clear.
Don’t duplicate the full text of your blog or github here. Just post the link for folks to click.
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
No trolling.
Resources:
Any issues on the community? Report it using the report flag.
Questions? DM the mods!
New Lemmy Post: ChatGPT’s voice, self-hosted? (https://lemmyverse.link/lemmy.world/post/15336896)
Tagging: #SelfHosted
(Replying in the OP of this thread (NOT THIS BOT!) will appear as a comment in the lemmy discussion.)
I am a FOSS bot. Check my README: https://github.com/db0/lemmy-tagginator/blob/main/README.md
When can I get one of these voices to read an epub on my phone? I’d love to have something like that
Librera FD as your reader app: https://www.f-droid.org/en/packages/com.foobnix.pro.pdf.reader/
Sherpa Onnx as your TTS engine: https://github.com/k2-fsa/sherpa-onnx
I recommend the piper TTS pretrained models, either Lessac medium or Kusal high/medium
Installing Sherpa Onnx TTS makes it an option to use as your system TTS voice
Localai.io
https://github.com/mudler/LocalAI
Regarding the TTS specifically, I remember looking into TorToiSeTTS back when this stuff was first coming out. You can generate ElevenLabs quality audio with it, but it’s insanely slow. In fact, when I was looking into it, it seemed like ElevenLabs may have been using a (much faster at the time) version of TorToiSe TTS, given the output is so similar.
According to the linked Github page, they seem to have solved the speed issues now, so it might be worth looking into. Of course, the other commenters have provided solutions that are pre-integrated into the LLM, but if you’re just looking for TTS this could be worth checking out. Also worth noting that this requires an NVIDIA GPU.
epub2tts: https://github.com/aedocw/epub2tts
Looks like a project that utilizes coqui-AI: https://github.com/coqui-ai/TTS
You mean just the text to speech part? Look into Piper
i use these two all the time for tts:
https://github.com/JarodMica/ai-voice-cloning / https://github.com/gitmylo/audio-webui
Oh WOW! Thanks to all who commented. Next time I get a chance I’m going to check these all out! 👍🏻 I hope others find this thread helpful too!
https://github.com/vndee/local-talking-llm
This is what OP looks for. It exists! Other repos only cover partially (e.g. either ollama or tts)