AI · alternatives · 2026
24 alternatives to Self-hosted voice AI agent for Asterisk/FreePBX
Hi HN folks ! I am the author of AVA, a self hosted AI Voice Agent that plugs into Asterisk/Freepbx so you own all the aspects of an AI Voice agent in your own infrastructure. It uses Asterisk native Audiosocket/RTP with python engine to run STT,LLM and TTS loop. The project support several full providers openai, gemini, grok, elevenlabs out of the box and also provides options to build custom pipelines by choosing different stt tts and llm. It also supports full local agent if you have a GPU with 25GB RAM which enables realtime conversation along with tool calling. I started this…
AVA is a self-hosted AI voice agent that integrates with Asterisk and FreePBX phone systems. It runs speech-to-text, language models, and text-to-speech processing on your own infrastructure using Python. The software… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Premium AI voice quality without the premium price tag.
2025 · async.com · its alternatives →
- 2
Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription – it anticipates the next likely word before it’s spoken. That makes it both fast (around 150 ms latency) and highly accurate. Scribe v2 Realtime outperforms every low latency transcription model across 30 commonly used EU and Asian languages – 93.5% accuracy, compared to Gemini 2.5 Flash (91.4%), GPT-4o MiniTranscribe (90.7%), and Deepgram Nova 3 (85%). It supports 90+ languages including…
2025 · elevenlabs.io · its alternatives →
- 3
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
Mar 2026 · georgelarson.me · its alternatives →
- 4
NovaVoice▲578Hey HN, Today I’d like to show what I’ve recently built with my 2 friends. We’ve called it Nova. The idea is to built all-purpose AI Voice Assistant, which is able to interact with mail, to-do apps, messengers and socials, task trackers, apps like UberEats, Notion and some other daily apps. How we decided to work on it: We’ve recently read YC Request for startups Summer25 and were inspired by the idea of AI Voice Assistant for Mail by YC partner Tyler Bosmeny. What we’ve got: We’ve gone a bit further than Assistant for mail only and connected Gmail, Todoist, Google Calendar, and…
Apr 2026 · novavoice.app · its alternatives →
- 5
- 6
The open-source framework for real-time AI voice
2025 · videosdk.live · its alternatives →
- 7
The first AI-powered voice assistant with privacy
2017 · snips.ai · its alternatives →
- 8
- 9
Welcome to Project S.A.T.U.R.D.A.Y. This is a project that allows anyone to easily build their own self-hosted J.A.R.V.I.S-like voice assistant. In my mind vocal computing is the future of human-computer interaction and by open sourcing this code I hope to expedite us on that path. I have had a blast working on this so far and I'm excited to continue to build with it. It uses whisper.cpp [1], Coqui TTS [2] and OpenAI [3] to do speech-to-text, text-to-text and text-to-speech inference all 100% locally (except for text-to-text). In the future I plan to swap out OpenAI for llama.cpp [4]. It is…
2023 · github.com · its alternatives →
- 10
Hi HN! Last year the project I launched here got a lot of good feedback on creating speech to speech AI on the ESP32. Recently I revamped the whole stack, iterated on that feedback and made our project fully open-source—all of the client, hardware, firmware code. This Github repo turns an ESP32-S3 into a realtime AI speech companion using the OpenAI Realtime API, Arduino WebSockets, Deno Edge Functions, and a full-stack web interface. You can talk to your own custom AI character, and it responds instantly. I couldn't find a resource that helped set up a reliable, secure websocket (WSS) AI…
2025 · github.com · its alternatives →
- 11
Hey HN! We were part of YC S24, ended up pivoting around. Made dictation that worked really well, and decided to go all in on agentic. We've done two major things. 1. Scribe is a revamp of our product. Continually learns your style (can get into details if comments want). TLDR; we fingerprint based off your edits, and make dictation sound more and more like you. Post-trained Llama 3.1 8b. 2. Dictation is completely free. Unlimited unpersonalized dictation for everyone.
Jul 2026 · willowvoice.com · its alternatives →
- 12
OpenWispr▲190100% local open source AI speech-to-text model
2025 · openwhispr.com · its alternatives →
- 13
Free AI transcription: convert video and audio to text, translate into 120 languages, download SRT, VTT, ASS or TXT, or export the video with subtitles on it.
2022 · freesubtitles.ai · its alternatives →
- 14
Voicebun▲189Hey HN, I built Voicebun as a pet project because I was frustrated with how locked-down and rigid voice agents still are—many tools are either closed platforms, lack deep customization, or charge a lot just to test ideas. I wanted a way to quickly spin up AI voice agents that I could fully control—from the voice itself to the logic behind every word. Voicebun is an open-source voice agent builder. You can: - Clone voices and generate audio using your own scripts and prompts - Dynamically change prompts based on user input - Add custom logic through functions and webhooks (e.g. hit an API,…
2025 · voicebun.com · its alternatives →
- 15
- 16
On-device speech AI for Mac, Windows, Linux & Android
Jun 2026 · github.com · its alternatives →
- 17
A fast, open-source voice assistant powered by Groq, Cartesia, and Vercel.
2024 · swift-ai.vercel.app · its alternatives →
- 18
Thinnest AI▲96Build Voice AI Agents in 100+ languages for ₹1.5/min
May 2026 · thinnest.ai · its alternatives →
- 19
- 20
TLDR: We created a personalised Andrej Karpathy tutor that can response to questions about his Youtube videos in sub 1 second responses (voice-to-voice). We do this using a voice enabled RAG agent. See later in the post for demo link, Github Repo and blog write up. A few weeks ago we released the worlds fastest voice bot, achieving 500ms voice-to-voice response times, including a 200ms delay waiting for a user to stop speaking. After reaching the front page of HN, we thought about how we could take this a step further based on feedback we were getting from the community. Many companies were…
2024 · educationbot.cerebrium.ai · its alternatives →
- 21
Powered_by▲29Custom AI agents for SMBs. agentic voice, email, sms, & more
2025 · poweredby.agency · its alternatives →
- 22
hi! video[0] The idea is you could carry around this hardware and ask it any questions about the conference. Who is speaking, what are they speaking about etc... it connects via WebRTC to a LLM and you get a bunch of info. This is a workshop/demo project I did for a conference. When I was talking to the organizers I mentioned that I enjoy doing hardware + WebRTC projects. They thought that was cool and so we ran with it. I have been doing these ESP32 + voice ai projects for a bit now. Started with an embedded sdk for livekit[1] that jul 2024 and been noodling with it since then. This…
2025 · github.com · its alternatives →
- 23
We gave the agents a voice. Sorry in advance.
Aug 2026 · fellowgeek.github.io · its alternatives →
- 24
Patter SDK▲10open-source SDK that gives your AI agent a phone number
Jul 2026 · github.com · its alternatives →
Also compare
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →