A CPU dictation engine, a GPU AI engine, three creative surfaces, 80+ template operations, and hands-free controls to drive all of it. Fully offline, fully private - and no graphics card needed to dictate. Here is how each piece works.
Engine one of two. NVIDIA's Parakeet TDT v3 transcribes on your CPU (int8 ONNX, ~670 MB) - English + 24 European languages, ready in seconds, and on fast natural speech it beat Whisper large-v3 running on a flagship GPU in our published benchmark (2.0 percent word error against 3.1). Whisper (five sizes, tiny to large-v3, CPU or CUDA) stays one click away for ~100 languages and all-GPU rigs.
Engine two of two - and the part your NVIDIA GPU is reserved for. Pair the raw transcript with any local LLM Ollama can serve - Gemma 3, Qwen 3, DeepSeek-R1, Llama 4 Scout, Phi-4, Mistral, whatever. 22+ in the catalog, custom prompts unlimited. The orchestrator parses param counts from model tags and estimates VRAM automatically, so 'pull a new model and it just works' is real.
This is the part no other app ships. Auto reads your card's total VRAM, measures Whisper's actual footprint, estimates the LLM's from its tag, and decides per-run whether to coexist or evict. Always-evict is safest for unknown models. Never-evict keeps recording snappy over AI speed. Auto picks the best of both for your hardware - you never tune a thing.
Both engines live on your machine. Whisper runs in a sandboxed sidecar talking JSON over stdio - no sockets, no shared memory. Ollama is bolted to 127.0.0.1. We don't ship telemetry, analytics, or even a license server you have to ping. Built for HIPAA, GDPR, SOC 2, and air-gapped boxes where 'we promise we won't' isn't good enough.
Record is the flagship. Compose and Voiceover turn the same local AI into a text studio and an audio studio - no mic required, no cloud, same engines.
Not everything starts with your voice. Paste any text - a rough draft, a colleague's email, meeting notes from another tool - pick a template and a tone, and let the local LLM reshape it. Same AI engine as Record, same templates, same tier access. No recording needed, no cloud, same local AI. Think of it as a private, local alternative to pasting into ChatGPT - except your text never leaves your machine.
Turn any script into narration without a recording booth. Four distinct personas (Clara, Marcus, Maya, Sam) crossed with eight delivery tones (Professional, Conversational, Warm, Calm, Bright, Authoritative, Storyteller, Energetic) give you 32 voice combinations - all synthesized locally on your CPU via Kokoro ONNX, no graphics card needed. No per-character billing, no cloud API, no rate limits. Export clean WAV files straight to your Downloads folder. Unlike ElevenLabs or Play.ht, your scripts never leave your machine and there is no usage meter ticking.
Templates are how Voxmelt turns a raw transcript or pasted text into exactly the format you need. Each template pack contains multiple tones - not just “rewrite” but “rewrite as a casual Slack reply” or “rewrite as a formal decline email” or “rewrite as a LinkedIn post.” Pick the action, pick the style, get the output. Every template works in both Record and Compose.
Vibe Dictation (6 tones), Rewrite (5), Proofread (4)
Diplomatic (5 tones), Persuasive (5)
AI Prompt Architect (9 tones), Coding Prompt (8)
Chat Responder (6), Email (5), Social Post (4), Video Script (4)
Meeting Recap (4), Notes (4), Translate (6 languages)
Write your own system prompt. Free: 1 slot, Pro: 5, Studio: 30
Dictate a rough idea; get back the exact scaffold your coding agent or LLM actually wants. The Coding Prompt and AI Prompt packs now turn a spoken sentence into deterministic state machines, self-verifying execution loops, agent-gated test beds, multi-agent routing, boundary-calibrated few-shot sets, and strict JSON mode - the prompt patterns power users hand-write today, now one tone away and 100% on your own hardware.
Autonomous control loop with an explicit trigger, goal, verification phase, and retry rule.
Deterministic state chart - states, transitions, guards, and invariants, no surprise side effects.
Isolated, assertive tests written as strict pass/fail gates an agent must clear.
Two or three refactor paths compared on complexity, performance, and overhead.
Forces step-by-step reasoning and a self-check before the model commits to an answer.
Locks output to strict JSON - schema in, zero prose or markdown out.
Splits the job across Planner, Critic, and Executor blocks with explicit routing.
Balanced edge-case examples that calibrate a small local model right on the decision boundary.
Polish raw spoken thoughts, rants, or logic into structured text in any vibe.
Turn raw spoken reactions into perfectly vibed replies for Slack, Teams, or text.
Convert spoken thought into a clean, structured LLM prompt.
Developer-ready spec for AI coding assistants.
Turn a recorded meeting, call, or standup into action items, decisions, minutes, or a TL;DR.
Compress a long voice memo, lecture, or brain-dump into bullets, an outline, a TL;DR, or study notes.
Strip away all the noise and keep only the dense nucleus - a one-line gist, a pure deliverables list, or a single atomic note.
Translate the transcript to another language.
Pick a persona, add your own instructions - runs 100% on your GPU, like every built-in.
Turn a spoken intent into a ready-to-send email - replies, follow-ups, declines, outreach, apologies.
Shape a raw thought into a post that lands - a LinkedIn post, an X thread, a hook, or a caption.
The everyday rewriter - paraphrase, shorten, expand, formalize, or sharpen any text.
Fix and tighten - grammar, clarity, conciseness, and direct active voice.
Recast a blunt or risky message so it lands well - tactful, calm, and relationship-safe, without losing the point.
Recast flat text into something compelling - confident, benefit-led, and hard to say no to, with the meaning intact.
Make any idea click - explain it simply, step by step, by analogy, or with a worked example.
Spoken idea to a script you can read on camera or send straight to the Voiceover page.
The engines do the thinking. These are how you run them - eyes off, hands free, never breaking flow.
A second, always-on Whisper tiny model (~0.3 GB VRAM) listens in the background and fuzzy-matches your speech against short, phonetically-distinct phrases. Say "go ahead" to start dictating, "wrap up" to stop, "copy that" to grab the clean text, "warm up" to load the AI - no hotkey, no mouse, no looking at the window. The listener steps aside the instant real dictation starts so it never fights your main model for the mic or the GPU, then resumes the moment you stop. Say it, and it happens.
Hands on the keys in Cursor or Copilot - say "go ahead", dictate the next prompt, "wrap up", "copy that", paste. Ship without breaking flow to hunt for a hotkey.
Cooking, soldering, mid-workout, or resting your wrists from RSI - run dictation start to finish by voice, from across the room.
Trigger capture and cleanup without alt-tabbing out of your scene. Your voice is the shortcut; the window can stay hidden.
Collapse Voxmelt into a tiny always-on-top pill you can drop anywhere and snap to any screen edge. It records in its own window with its own Whisper pipeline, mirrors your theme live, and shows the transcript and AI output in compact tabs - so you can dictate into any app without the full workbench in the way. Pair it with No-Hands Mode and the main window can stay closed in the tray while you run the whole flow from the pill. Out of the way, one tap away.
Park the pill in a corner and dictate into Slack, email, chat, or docs all day - no full workbench hogging the screen.
Keep your work full-screen; the pill rides the edge of a laptop panel or a second display, always one tap away.
Float it over the IDE and talk your prompts straight into Copilot or Cursor - eyes on the code, not on a separate app.
Best-in-class dictation on the CPU you already own - and if there is an NVIDIA GPU in your rig, a full local AI studio on top. RTX Spark-ready when the new hardware lands.