AudioGen Studio

NOIR CALL — End-to-End in One Tool

A 16-line audio drama scene: Viktor, a tired NY detective, calls Laura from the streets of Manhattan. Two voices, telephone-filter on her side, rain and city atmosphere, slow jazz vinyl bleeding through her apartment, a final outro of his footsteps walking off. Every asset on this page was generated, processed, and arranged inside AudioGen Studio — no external editor touched.

Seven Steps, One App

No tab-hopping between tools. The same desktop app moves the project from "voice description prompt" to "mastered MP4 with audio-reactive visuals" — and back, when you want to iterate.

Describe a voice in plain English, get back a usable speaker identity. Qwen3-TTS turns a prose description ("A weathered American male voice in his early forties, deep baritone with a slight gravel from too many late nights…") plus a 25–30 second sample text into a custom voice that gets saved into the Voice Library with language, gender, and bucket. The library on the right shows speakers organized by project — TheBlackVeil, Charlie_Project, NOIR CALL — and you assign saved voices straight to the Script tab's Speaker 1 / Speaker 2 slots.

Voice Designer — generating "Laura" from a prose description, ready to assign to Speaker 2 in the Script tab.

Paste a script, assign saved voices to speakers, pick a Chatterbox engine variant, and generate the whole conversation line by line. The Mood Pill bar applies inline [soft] / [firm] / [urgent] / [whisper] tags that Chatterbox's mood-aware variant respects per line. Auto-generate-then-approve walks through the conversation and lets the operator accept, regenerate, or re-mood any single line without re-running the rest.

Script tab — NOIR CALL loaded with both speakers assigned, mood pills above the text, per-line approval queue below.

MMAudio for short concrete sound effects (phone pickup, taxi pass on wet asphalt, footsteps), AudioLDM2 in the same pipeline for longer atmosphere loops. Single-element prompts work better than stacked ones — "wet asphalt, tire swoosh" beats "rain AND traffic AND horn AND footsteps" every time. Generated clips save into the SFX Library with category tags (Ambience, Foley, Impact, UI) and drop straight onto Composer tracks.

SFX Studio — generating a tavern atmosphere clip with MMAudio, ready to save as a categorized library entry.

ACE-Step XL Turbo via Diffusers — MIT-licensed weights, 20× realtime, runs comfortably on a consumer GPU. Six modes: Generate a fresh track, Extend an existing one, Add Intro / Add Outro, Repaint a drag-selected region without touching the rest, or Cover an existing track in a different genre. Style presets ("Lo-Fi Cafe", "Cinematic Build", etc.) prefill prompt + parameters with proven defaults that you edit on top. Lyrics field is optional — leave blank for instrumental, add [verse] / [chorus] / [bridge] tags for sung output.

Music Studio — generating a lo-fi hip-hop loop with vinyl crackle, BPM 80, C minor. Preset "Lo-Fi Cafe" prefilled the defaults; the rest is overridden on top.

Per-speaker and per-line effect chains for the whole conversation. Pick a session from the dropdown, see every line organized by speaker on the left, build an effect chain on the right. Apply a chain to an entire speaker (Laura gets the Telephone-Filter — High-Pass 300 Hz, Low-Pass 3400 Hz, slight saturation, compressor, gain trim — for the whole call) or override one specific line for emphasis. Compare button A/Bs original vs. processed; the Export FX Combined button writes the rendered version back as a session-bound artifact.

FX Studio — Laura selected, Lo-Fi (telephone) preset loaded, chain ready to apply across all 7 of her lines.

Same FX Studio shell, Music tab. Mastering chains use a different preset category — "Music Master Streaming (-14 LUFS · Spotify/Apple)" is the daily-driver default with High-Pass 30 Hz, two Presence Boosts, Compressor, Limiter, LUFS Normalize. Below the music library: Separate Stems runs Demucs at ~6× realtime, splitting any track into drums / bass / vocals / other. The stems become children of the master track in the library and can be dropped into the Composer as four parallel lanes for independent volume / FX / muting — or remixed back into a new master.

FX Studio Music tab — Jazz_1940_Intro split into 4 Demucs stems (bass / drums / other / vocals), Music Master Streaming chain (6 effects) applied.

Where everything comes together. Voice sessions auto-sync from the Script tab as two parallel speaker tracks with proper gaps between lines. SFX clips drag from the library onto their own lanes. Music sits on a dedicated music lane (or four lanes if you dropped stems). Per-track color, type icon, drag-handle rename, individual volume. Auto-snap to clip edges, BPM beats, and markers. Auto-crossfade on overlapping music / SFX / ambience clips. Multi-select with Alt+Drag, ripple-edit with Alt+Shift+Drag. Two export targets: a single WAV / MP3 of the audio mix, or an MP4 with the audio plus audio-reactive visuals (spectrum bars, waveform pulse) overlaid on a still cover image.

Composer — NOIR CALL session laid out across voice lanes (Viktor / Laura), SFX track (footsteps, taxi), music lane with the vinyl loop. Video FX panel on the right configures audio-reactive overlays for MP4 export.

Seven Steps, One Final Mix

Every step above, in one finished audio drama clip. Two voices, telephone filter on Laura's side, MMAudio rain / vinyl / footsteps, ACE-Step jazz score under it all, mastered to -14 LUFS via the FX Studio chain, exported from the Composer.

Tech Stack

Every model runs locally on a consumer GPU. No cloud APIs, no subscriptions, no telemetry — the whole pipeline is offline-capable.