Spatial Audio Raven Preamp

I hope you folks like the Raven (which are built and sold by Spatial Audio Labs). It’s a miniature version of the power amp, with one stage of gain instead of three. It has both RCA and XLR inputs, with the balanced input going straight to the 6SN7 grids, and the RCA going through a studio-quality input transformer (which converts the signal to balanced). The volume control is a special-order Khozmo dual mono unit, with volume and L/R balance on the remote control. The output is also transformer coupled, with both RCA and XLR balanced outputs.

Don Sach’s previous preamp had a special SRPP circuit, which used clever noise-cancellation techniques to reject power supply noise. The Raven similarly uses inherent circuit balance to also reject power supply noise ... although there isn’t much, since the power supply regulator itself has 130 dB of noise rejection.

Probably the biggest sonic difference is the previous Don Sachs preamp used a cathode follower and a very high quality coupling cap in the final stage, while the Raven uses transformer coupling to accomplish the same thing.

They are custom-design Cinemag, optimized for our circuit. They are not off-the-shelf parts, which have bandwidth problems with the output impedance of the 6SN7.

The 6SN7 is one of the best tubes ever made, but is not easy to match with most transformers. That’s where Cinemag came in, who saw the 6SN7 as a fun challenge. Several prototypes later (design, computer model, build, measure, listen, and repeat the cycle), we arrived at the production models we’re using now.

The Khozmo volume control is also optimized for this preamp, with a different signal path than most preamps. The Raven is balanced throughout, from input to source selector to volume control to vacuum tube to output.

One nice thing about transformer coupled balanced construction is the risk of sending DC pulses to a delicate transistor power amp are greatly reduced. (Even when a transistor amp is switched off, a DC pulse of more than a few volts can damage the input transistors.)

P.S. How does the output transformer protect a power amp? First, there’s a 4.5 times step-down ratio, reducing unwanted transients by a similar ratio. Second, the circuit itself is balanced, instead of a single-ended cathode follower exposed to a hundred volts or more. Circuit balance is typically 3% or better, reducing potential transients by a similar amount (about 30 dB). Third, and most important, transformers can never pass DC, unless the windings themselves have failed. By contrast, capacitors may pass "leakage current" and gradually short out as they age (a well-known problem when restoring vintage electronics).

Of course, things were a little bigger back then. This entire rack is one channel of amplification. Two racks were typically used, with instant changeover in case of failure while the movie was presented.

Yes, I’m curious too. Oddly enough, even though I designed the Raven in 1998, I never actually heard one until the Seattle show last June 2023.

Don and I agreed it was good to choose tubes that were (A) in current production from respected vendors with an excellent track record of reliability, and (B) offer the option of using classic vintage tubes for folks who want to do that. So no unobtainium surplus tubes like 12SN7, ancient 101D’s, or using power-tube DHT’s in a preamp stage that require exotic anti-microphonic isolation systems.

We want keep it simple and focus on the most linear circuit possible. The entire signal path is transformers, wire, and vacuum tubes, in a fully balanced configuration similar to Western Electric line amplifiers from the Thirties. It’s actually rather difficult to "tune" subjectively because there isn’t much you can tweak.

One thing I can say: when you get rid of the last coupling cap in the circuit, surprises await.

One of the points of inspiration: the late-Twenties Western Electric Model 43A amplifier, used in the WE Mirrophonic theatre systems.

I started my career in audio with the invention, patenting, and prototyping of the Shadow Vector quadraphonic decoder, back in 1973. That SQ/stereo decoder was specifically designed to preserve ambient cues and spatial impression, without adding anything like a reverb circuit, or taking anything away from the source material.

There’s a lot of content in a 2-channel recording that is destroyed on playback, or is below the threshold of audibility. This is not the fault of the recording, but the playback system. In general terms, this is low-level information with L/R phase angles between +/- 45 and 180 degrees. A (very good) quadraphonic decoder will route this information to the sides and rear, depending on phase angle, without affecting the frontal image or deforming it. Ideally, random-phase reverberation (from spaced mikes, reverb plate, or good digital reverb) should appear as an evenly weighted sphere around the listener, with no bumps, holes, or hotspots, just as it is in real, physical acoustic spaces. Again, this random-phase information is present on all stereo recordings with even a slight sense of space, because studio professionals consider "dry" vocals intolerable, so some reverb is added on just about everything. And the correct method of presentation is spherical, to match real acoustic spaces.

Unfortunately, 2-speaker playback abbreviates the most realistic spatial presentation, although some speakers preserve a vestige of it. Smooth dispersion patterns, freedom from resonant energy storage in the drivers, and freedom from diffraction artifacts (no sharp cabinet edges) can allow the sound space to leave the confines of the speaker cabinet (as it should in a good loudspeaker). Most listeners never hear this, but it’s still there on the recording, waiting to be heard. (And no, it doesn’t take 11 speakers to preserve spatial information. That’s for special effects in movie theaters.)

For some reason, electronics can also affect the spatial impression. I suspect that many electronics destroy, or alter, the low-level interchannel signals that convey this spatial impression, somewhat akin to MP3 lossy compression discarding "unnecessary" low-level bits. Nothing as violent as that happens in normal electronics, of course, but still, it subjectively sounds like bit reduction, with a loss or "air", spatial realism, and realistic tonality. I am not sure of the mechanism, but high-order nonlinearities, power supply switch-noise grunge, correlated noise, and odd, hard-to-pin-down capacitor colorations (possibly chemical reactions in the dielectric) all seem to play a role in shrinking the sound stage and destroying the ambient impression.

That’s why the Raven and Blackbird minimize energy storage in the signal path. There are no feedback loops, either local or overall. There are no coupling caps, on the input, between stages, or on the output. The balanced circuit presents a nearly constant demand on the power supply, which is further smoothed by the shunt regulator tubes in the preamp. The signal goes in, is fed to a Class A balanced pair of very linear vacuum tubes, and is transformer re-balanced on the way out. No signal recirculation, no phase inverters, no cathode followers, and no secondary side chains (DC servo circuits, dynamic loads, etc.), even at very low levels (which is why it is so quiet).

That's why I was pleased to collaborate with Don Sachs, starting a couple of years ago. I already owned his preamp, and I was quite impressed he had decades of experience on the insanely complex Citation I and Citation II preamp and power amps. Those products are not for the faint of heart ... Stu Hegeman was a seriously out-there guy, and a legend back in the Sixties.

I expect to be there for the Oregon Triode Society demo as well. Maybe I’ll meet some old friends ... I joined the OTS way back in 1990 or so, at the second meeting.

Way too far to drive all the way from the Denver metro area, so I’ll fly again, but take Business Class this time. My days of flying in Cattle Class are over, can’t handle the crowds or the itsy-bitsy seats the airlines use now. I do miss the Amtrack sleeper service from Denver to Portland ... that was a very nice train ride.

Looking back, I look at the incredible complexity of that Shadow Vector patent (which I invented solo, unlike the three-person CBS team) and how I really jumped in at the deep end of the pool when I joined the hifi biz professionally. Working as a commissioned salesman was such a horrific experience I was strongly motivated to get out of Los Angeles and move to Audionics in Portland, Oregon.

Although I had my differences with Audionics, they did believe in me enough to hire me to build the prototype, which took two years of hard work. That stretch was one of the biggest pushes I’ve done, along with finally completing my Psychology degree a few years later. Speaker design was considerably easier.

Shadow Vector Patent