DeciBench
pytest for voice AI agents. Local-first & open source.
What it does
Decibench is a local-first testing framework for voice agents. 🎙️ It simulates callers, streams audio to your agent over WebSocket/Twilio/ElevenLabs, transcripts responses, and grades them across 10 metrics like latency, hallucinations, and interruptions. Run it offline with Ollama & local Whisper. 100% private with a built-in PII redaction engine. Zero telemetry, Apache 2.0. No SDK needed. 🛠️
Does a similar job
all alternatives →
- AOAn open source framework for voice assistants2024 · github.com · ▲346
I've been obsessed for the past ~year with the possibilities of talking to LLMs. I built a bunch of one-off prototypes, shared code on X, started a Meetup group in SF, and co-hosted a big hackathon. It turns out that there are a few low-level problems that everybody building conversational/real-time AI needs to solve on the way to building/shipping something that works well: low-latency media transport, echo cancellation, voice activity detection, phrase endpointing, pipelining data between models/services, handling voice interruptions, swapping out different…
- IBI built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570
I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com