Pipecat
AI
voice assistant framework
SHOW HN2024
How HN took it
3 positive, 6 neutral or asking, 0 mixed, 1 critical, out of 10 comments about the project. Thread score +0.17.
Idea: 1 for, 1 againstDocs: 1 for, 0 againstExecution: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Open source implementation of a needed voice AI layer
From 2 comments
Nice to see an open source implementation, i have been seeing many startups get into this space like https://www.retellai.com/, https://fixie.ai/ etc. They always end up needing…
awenix on HNThe whole VAD thing is very interesting, keen to learn more about how it works and especially with multiple speakers!
orliesaurus on HN
Examples like speech-to-speech and translation demos look impressive
From 2 comments
That's absolutely amazing, both visually and technically! Do you share any insights of the development process, perhaps some code?
TomTom101101 on HNHere's a translation demo in Pipecat using the now ancient and arthritic GPT-4 Turbo model. :-) https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot As…
kwindla on HN
Objections
Pipelines of STT, LLM and TTS seem inferior to native speech-to-speech models like GPT-4o
From 2 comments
Yeah, same question here. Building pipelines for bridging LLMs and TTS and STT models with lower latency is fine and all, but when you compare to a natively multimodal model like…
avarun on HNI wonder how the just announced "GPT-4o" with real-time voice impacts projects like this? The demo on real-time multi language translation conversation blew me away!
bamazizi on HN
Speech-to-speech support is not visible in the code
From 1 comment
Your project is amazing and I'm not trying to take away from what you have accomplished. But..I looked at the code but didn't see any audio-to-audio service or model. Can you…
ilaksh on HN
Requests
Add speech-to-speech or audio-to-audio model support
From 2 comments
This is great but we really need an audio-to-audio model like they demoed in the open source world. Does anyone know of anything like that? Edit: someone found one:…
ilaksh on HNYour project is amazing and I'm not trying to take away from what you have accomplished. But..I looked at the code but didn't see any audio-to-audio service or model. Can you…
ilaksh on HN
Live translation of phone calls
From 2 comments
How would I go about using this to live translate phone calls?
35mm on HNTo talk to people in languages I am not fluent in. Whisper is too slow and doesn’t allow interruption.
35mm on HN
Questions
How speech-to-speech models work and how they differ from pipelines
From 1 comment
How do speech to speech models work? Do they just that many more tokens to capture nuances of spoken language?
j-bos on HN
How the VAD works with multiple speakers
From 1 comment
The whole VAD thing is very interesting, keen to learn more about how it works and especially with multiple speakers!
orliesaurus on HN
Impact of GPT-4o on projects like this
From 1 comment
I wonder how the just announced "GPT-4o" with real-time voice impacts projects like this? The demo on real-time multi language translation conversation blew me away!
bamazizi on HN
Alternatives named
LiveKit Agents
From 1 comment
LiveKit Agents, which OpenAI uses in voice mode is also open source: https://github.com/livekit/agents
russ on HN
Vapi
From 1 comment
Adding to your list: https://vapi.ai -- really nice tools. (I try to keep up with all the different layers/players in this space.)
kwindla on HN
Retell AI
From 1 comment
Nice to see an open source implementation, i have been seeing many startups get into this space like https://www.retellai.com/, https://fixie.ai/ etc. They always end up needing…
awenix on HN
Fixie.ai
From 2 comments
Nice to see an open source implementation, i have been seeing many startups get into this space like https://www.retellai.com/, https://fixie.ai/ etc. They always end up needing…
awenix on HNWe're (fixie.ai) working on on our SLM (speech language model). We'll release something soon to play with :)
zkoch on HN
Bolna
From 1 comment
We're also building bolna an open source voice orchestration: https://github.com/bolna-ai/bolna
xan_ps007 on HN