IRCAM SuperVP Transform — User Guide
Praat AudioTools bridge to IRCAM SuperVP for analysis-driven spectral transformation, resynthesis and creative processing. Praat supplies F0 and Intensity analysis; the Python backend builds verified SuperVP commands and control curves, runs the engine, and returns both the sound and a manifest of the process.
What this does
SuperVP Transform connects Praat's analysis tools with the IRCAM SuperVP command-line engine. It is designed as an offline analysis–resynthesis environment rather than a real-time effect.
- Praat exports the selected Sound object(s) to WAV.
- Praat analyses pitch and intensity. Pitch can be estimated automatically with a two-pass range finder or with a user-selected range.
- The Python backend converts analysis into SuperVP BPF/control files and assembles the exact command line.
- SuperVP performs the transformation/resynthesis.
- Praat imports the result and can draw the analysis, control curves, spectrograms and executed commands.
Quick start
- Install and activate a licensed copy of IRCAM SuperVP. On the current Windows setup the executable is typically
C:\Users\User\SuperVP\bin\supervp.exe. - Place
supervp_transform.pyinplugin_AudioTools/py/. - Select one Sound in Praat. Select two Sounds only for Spectral cross synthesis.
- Run
IRCAM_SuperVP_Transform.praat. - Choose a processing mode, quality profile and pitch range.
- Click Next, adjust the mode-specific parameters, then click Apply.
- The dialog remains open so parameters can be adjusted and re-applied without restarting the script.
Processing modes
| Mode | Main SuperVP mechanism | What it does |
|---|---|---|
| Voice age | -age | Built-in voice ageing/rejuvenation. Positive values sound older; negative values younger. |
| Gender | -female / -male, optional -transenv | Built-in gender transformation, optionally reinforced with an additional formant/envelope shift. |
| Age + gender | Two SuperVP passes | Runs Age first, then Gender. |
| Flatten pitch | -transke BPF | Moves the measured F0 contour toward its median or a user target. Amount 1 = flat; 0 = unchanged; negative values exaggerate the contour. |
| Vibrato | -transke BPF | Deterministic sinusoidal pitch modulation, optionally applied only to voiced frames with onset fade-in. |
| Organic vibrato | -trmdlp | SuperVP randomly redraws vibrato rate and depth within user-defined ranges. |
| Harmoniser | -transke + waveform mixing | Creates a transposed copy and mixes it with the original at a fixed musical interval. |
| Formant shift | -transenv | Spectral-envelope shift with Constant, Ramp, Follow F0, Follow Intensity and Wander shapes. |
| Time stretch | -D | Constant or time-varying dilation. Shapes include constant, voiced-only, unvoiced-only and ramp. |
| Tremolo | -ggain, -transenv, -trmdle, or -gtremolo | Four tremolo engines: amplitude, spectral-envelope, constant SuperVP envelope tremolo, and native SuperVP tremolo with sine/triangle/square/saw waveforms. Depth can follow Praat Intensity. |
| Breathiness | -Gcross | Creates a whispered copy by combining the source spectral envelope with noise fine structure, level-matches it, then blends it with the original. It no longer relies on -Gnoise. |
| Spectral cross synthesis | -Gcross | Combines amplitude and frequency structure from two Sounds. Simple mode is spectral cross-coupling, not a linear source mix; Advanced mode exposes X/x/Y/y weights. |
| Dynamic gate | -ggain BPF | Time-domain output gain derived from Intensity. Useful for gating, but it does not remove noise inside the spectrum. |
| Spectral denoise | -avseg/-OM1 → -Fsub | Two-pass spectral subtraction. SuperVP first learns a noise spectrum from a noise-only time segment, then subtracts that model from the full signal. |
| Spectral phase diffusion | -rnd_force, -rnd_voi, -rnd_stval, -rnd_ff, optional -shape 1/-rnd_sin | Uses SuperVP phase randomization as a creative effect. Separate control is available for non-sinusoidal material, noise above the VUF and—when sinusoidal separation is enabled—sinusoidal components. |
| Frequency shift | -Ffshift | True frequency shifting in Hz. Every partial moves by the same Hz amount, producing inharmonic spectra unlike pitch transposition in cents. |
| Diagnostics | SuperVP help interrogation | Reads the installed build's help and reports quality flags and creative features that are actually supported. |
Quality profiles & pitch analysis
The quality profile controls analysis-window behaviour, overlap, transient handling and selected SuperVP quality options. Flags are emitted only when the installed SuperVP help confirms them.
| Profile | Purpose |
|---|---|
| Standard (v2 behaviour) | Compatibility profile. Keeps the established processing path with no new v3 quality flags. |
| General | General-purpose high-quality analysis. With voiced F0 it uses Praat's pitch track for an F0-adaptive window (-F0 + -Mauto). |
| Voice | Monophonic speech/singing profile. Adds voice-oriented windowing and, where applicable, adaptive True Envelope and perceived-loudness preservation (-envpl 1). |
| Percussive | Shorter window and transient-oriented analysis. |
| Smeared | Long analysis window with transient preservation intentionally reduced for a more blurred/smeared result. |
Adaptive True Envelope
In suitable envelope-based modes, the General and Voice profiles can use Praat's measured F0 directly in SuperVP:
-F0 f0.bpf -Afft +<95th-percentile-F0>Hz
This lets the envelope order adapt to the source rather than using one fixed envelope order.
Pitch range
The main dialog offers:
- Auto (two-pass) — initial search across approximately 30–3000 Hz, followed by quantile-based narrowing.
- Speech — 75–500 Hz.
- Singing — 80–1000 Hz.
- Instrument — 40–2000 Hz.
- Wide — 30–3000 Hz.
- Custom — user-defined floor and ceiling.
Pipeline
2. Praat analysis — F0 and Intensity → BPF files.
3. Python bridge — analysis-derived BPFs + capability-checked SuperVP command.
4. SuperVP — spectral analysis / transformation / resynthesis.
5. Manifest — exact commands, quality flags, notes and control curves.
6. Praat import — processed WAV + optional visualisation.
BPF control files
Most control curves are two-column text files containing time value. Depending on the mode, values can represent F0 in Hz, transposition in cents, linear gain, frequency shift in Hz, stretch factor, tremolo depth, or another SuperVP control parameter.
Spectral denoise is a special two-pass process
Pass 1: -avseg start,end -OM1 noise_profile_M1.sdif
Pass 2: -Fsub noise_profile_M1.sdif -avbeta ... -avsfac ... -avrelax ... -avgamma ... -avdet ...
The first pass creates an SDIF noise model containing the mean and standard deviation of each spectral bin. The second pass performs Bark-smoothed spectral subtraction.
Important mode parameters
| Mode | Key parameters | Default / meaning |
|---|---|---|
| Flatten pitch | Target pitch, Flatten amount | Target 0 = median F0; amount 1 = flat, 0 = unchanged. |
| Vibrato | Rate, Depth, Voiced only, Onset fade | Deterministic F0 modulation in cents. |
| Organic vibrato | Rate min/max, Depth min/max, New values every | Defaults: 4.5–6.5 Hz, depth 20–60, new values every 0.4 s. |
| Formant shift | Shape, Shift, End, Modulation depth, Wander rate, Seed | Depth meaning depends on selected shape. |
| Time stretch | Stretch factor, Stretch shape | Default factor 1.5. |
| Tremolo | Type, Native waveform, Intensity mapping, Rate, Amplitude depth, Envelope depth, Smoothing | Native -gtremolo uses SuperVP's internal waveform; the Rate field does not control that native mode. |
| Breathiness | Amount, Seed | Default amount 0.4. |
| Spectral cross synthesis | Control type, Spectral cross coupling, X/x/Y/y, Source-2 fit | Simple coupling 0.5 is not a 50/50 waveform mix; it cross-couples amplitude and frequency structure. |
| Dynamic gate | Threshold below peak, Smoothing | Default threshold 30 dB, smoothing 40 ms. |
| Spectral denoise | Noise sample start/end, Maximum reduction, Noise estimate std factor, Relaxation, Subtraction type, Deterministic noise | Defaults: 0–0.25 s, 20 dB, 1.0, 30 ms, amplitude subtraction, deterministic handling off. |
| Spectral phase diffusion | Sinusoidal randomization, Non-sinusoidal randomization, Noise randomization at VUF, Full randomization frequency, Separate sinusoids | Defaults: 0, 0.15, 0.30, 18 kHz, separation off. Levels are fractions of π. |
| Frequency shift | Shape, Shift, Ramp end, Modulation depth, Wander rate, Seed | Default shift −50 Hz; true Hz shift, not transposition. |
-rnd_sin is meaningful only when SuperVP separates sinusoidal components. Enable Separate sinusoids (-shape 1) for a monophonic/single-source signal when you want independent sinusoidal randomization.
Visualization & manifest
When Draw visualisation is enabled, the Praat picture is driven by the manifest written by the Python backend. It can include:
- input and result waveforms/spectrograms,
- Praat F0 and Intensity analysis,
- every control curve actually sent to SuperVP, with units,
- quality flags and notes,
- shortened SuperVP commands for readability.
The manifest also stores the full executed command lines (cmd_full) so the exact processing path can be inspected or reproduced.
FAQ / troubleshooting
Point the first dialog's SuperVP executable field to the installed command-line binary. The path is remembered between sessions.
Activate the installed build with the valid IRCAM activation key file before using the Praat bridge. Activation is handled by SuperVP itself, not by this script.
Move the noise-learning interval to a section that contains only background noise. The learned SDIF model is used as the spectrum to subtract from the entire sound.
Enable Separate sinusoids (-shape 1; mono source). Without sinusoidal separation, the script intentionally ignores the sinusoidal randomization value and still applies the non-sinusoidal/noise controls.
Dynamic gate changes output gain over time using -ggain. Spectral denoise estimates a noise spectrum and removes it inside the time-frequency representation using -Fsub. They solve different problems.
-transke changes frequencies proportionally (musical transposition). -Ffshift adds the same number of Hz to every partial, usually making harmonic sounds increasingly inharmonic.
Run Diagnostics after changing SuperVP versions. The backend reads the help of the installed build and reports which newer flags and creative features are actually available.