Open source Retell AI alternatives

Why we no longer use LangChain for building our AI agents

“I don’t think that’s fair to Llama-Index. LI is much more focused, better documented and frankly way easier to use than LangChain, with much lower - or negligible - cognitive overhead. Plus, it plays nice with most everything else. Even if you’re mostly working just with a…”

Why we no longer use LangChain for building our AI agents

“I think this is another crucial part. Right now, writing prompts is kinda like writing hand-crafted assembly back in the day where that was routine because there was simply no other way to get good results out of hardware in many cases - but also because the tasks that are…”

Bark – Text-prompted generative audio model

“This tech will be used by crooks to automate attacks. Generate the language using GPT-4 and the audio using Bark, and then start making phone calls. Because it’s open source, all you need is GPUs. This is not a criticism. I’m impressed and grateful for the openness. Everyone…”

Bark: A transformer based text to audio system

“>Yeah I was trying to figure out how good it was in Korean. The cadence and flow was pretty good but there was kind of artifacts in the audio. Then I check the samples of the default audio prompts for Korean any my god, they were godawful. Switching it up made a world of…”

Windows process crashes when the GPU model is unloaded

“Thanks for your work first. It's useful. Howerver, there's still something wrong. It returns -1073740791 (0xC0000409) when dealing with a audio file in chinese. I have defined a function in which the variable 'result' is used to accept the 'segments' returned by the…”

Could not load library libcudnn_ops_infer.so.8

“` Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory ` I'm using "nvidia/cuda:12.2.0-base-ubuntu20.04" image on google cloud with nvidia t4 gpus. The normal whisper package model works fine on…”

Show HN: Open-source customizable AI voice dictation built on Pipecat

“Hey, sorry if the examples given were not robust, but because this is built on Pipecat, you can actually very easily swap to a local LLM if you prefer that, and the project is already set up to allow you to do that via environment variables. The integration to set up the WebRTC…”

Show HN: Open-source customizable AI voice dictation built on Pipecat

“Thanks for the feedback, probably should have been clearer in my original post and in the README as well. Local inference is already supported via Pipecat, you can use ollama or any custom OpenAI endpoint. Local STT is also supported via whisper, which pipecat will download and…”

[CHANGELOG] v6.2 just released!

“Just a handy issue to be notified of latest changes and micro-releases (we will mostly changing the models)”

[FORMATS] Most important export formats?

“As everybody knows, the VAD now exists as an ONNX model (`onnx-runtime`) and as a `jit` (PyTorch TorchScript) model. Can you please shorlist the remaining most important export formats, i.e. TF, OpenVINO, etc? We need some data / votes to make a shortlist. To make it simpler - I…”

Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

“Kokoro voices were the non-human actors directed by Opus, featured in the sound performance "God Bless the United States of Aliens". A theatrical adaptation of a liturgical texts, a surveilled mass ceremony at a protesting Christian church, being exhibited at the 61st Venice…”

Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

“I love Kokoro. I use it to read ebooks that don't have audiobooks and it works pretty good for that. I have a Python script that reads epub/html, runs the model and writes mp3s. Kokoro supports a limited number of languages. I've had to resort to other models to support Dutch,…”

Request is not going to eleven labs

“2ager} [__init__] task initialization completed 2025-07-10 22:28:42.395 | 2025-07-10 16:58:42.394 INFO {task_manager} [__init__] Conversation config {'optimize_latency': True, 'hangup_after_silence': 10, 'incremental_delay': 1200, 'number_of_words_for_interruption': 2,…”

Got the repo kinda working

“Right now these are my logs from a recent call ``` Server running on port 3000 Twilio -> Starting Media Stream for MZ1cbaeb64da6297ccb08a8cf316d2fe6c Interaction 1: TTS -> TWILIO: Hello! I understand you're looking for a pair of AirPods, is that correct? Twilio -> Audio…”

I get this issue

“when i run "npm run outbound" i get this issue ![image_2024-03-10_093319126](”

Launch HN: Vocode (YC W23) – Library for voice conversation with LLMs

“Enterprise is not in Vocode's target market. Target market is startups and individual devs. There are bloated and over engineered voice chat services for LLMs for Enterprise already.”