Vaaani

What it does

Vaani is an 18-layer acoustic pipeline for IELTS/TOEFL Speaking — Praat formants, peer-reviewed rhythm, syntax-tree grammar → Contrastive Interference Function against 8 Indian-L1 attractors (Bengali + Hindi on Svarah; six on published phonetics). No LLM. No GPU. Same audio = same band. Every L1 callout needs two-piece evidence: acoustic detection AND catalogue match — otherwise unlabelled, never pinned to an L1. Vaani tells you what it measured, how confident, and what it couldn't.

• 
  VaaniJun 2026 · vaani.media · ▲318

  Lip-synced AI dubbing for creators, brands and studios

• IT
  I trained a 9M speech model to fix my Mandarin tonesJan 2026 · simedw.com · ▲469

  Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web. Grades per-syllable pronunciation + tones with Viterbi forced alignment. Try it here: https://simedw.com/projects/ear/

• 
  Gan.AI TTS Model & API Playground2024 · ▲344

  First TTS model to support all 22 Indic languages + English

• IB
  I 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…

• NT
  Neural text to speech with dozens of celebrity voices2020 · vocodes.com · ▲462
• 
  Voysis2018 · ▲111

  The complete independent Voice AI platform

• 
  Browzer▲426

  Put your technical content on autopilot

  Growth · 14d ago · trybrowzer.com

• 
  AstraPixels▲267

  ​​A pixel-art solar system at its real current positions.​

  Growth · 30d ago · astrapixels.com

• 
  Brew ▲905

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲897

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲805

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲796

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• NW
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  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
  Files.md – Open-source alternative to Obsidian▲730

  Dev tools · May 2026 · github.com