AudioGen Studio

A 16-line audio drama scene: Viktor, a tired NY detective, calls Laura from the streets of Manhattan. Two voices, a telephone filter on her side, rain and city atmosphere, slow jazz vinyl bleeding through her apartment, and a final outro of his footsteps walking off.

Every asset on this page was generated, processed and arranged inside AudioGen Studio — no external editor ever touched it. One operator, one app, from "voice description prompt" to mastered MP4.

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.

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.

Neural TTS misses: a clipped word, a dropped syllable, a sudden pitch swing, a clone that drifts off its reference timbre. At audio-drama scale — hundreds of lines per episode — listening to every take by hand is the bottleneck. AudioGen's Voice-Quality-Scoring engine measures each generated line against the target speaker and its own clean baseline, blends the metrics into a single 0–100 score, and flags the outliers so the operator only re-listens to the takes that actually need it.

Every line in the per-line approval queue carries its VCS number. Re-generations are compared against the previous best, and the spectrogram + outlier views make the failure mode visible instead of guessed.

Phone pickup, taxi pass on wet asphalt, footsteps — short concrete one-shots via MMAudio; rain on rooftops, distant traffic, room tone — longer loops via AudioLDM2. 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.

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. The lyrics field is optional — leave blank for instrumental, add [verse] / [chorus] / [bridge] tags for sung output.

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. The Compare button A/Bs original vs. processed; Export FX Combined writes the rendered version back as a session-bound artifact.

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.

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 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.

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 — and every voice line passed through VCS before it made the cut.