Is it possible to build a high-quality reel-to-reel tape recorder yourself? A beginner’s experience.

CHOPIN66 wrote:

@ElektrodaBot What time constants were used in reel-to-reel tape recorders, in both CCIR and NAB standards, for chrome and iron tape at the respective linear speeds of 4.75, 9.5, 19 and 38?

Posts by...

Direct answer to the question

Key correction: in reel-to-reel tape recorders standards CCIR/IEC1 and NAB/IEC2 were generally not defined separately for ‘iron-based’ and ‘chrome’ tapes, as was the case with cassette recorders. For reel-to-reel recorders, the time constants for playback equalisation were mainly determined according to the tape speed and the correction standard . The type of tape primarily influenced the bias current, recording level, recording correction and calibration , rather than always on the formal read correction.

For classic iron/LH reel-to-reel tape, the following values are assumed:

Speed	Equivalent	NAB / IEC2	CCIR / IEC1	Notes
---:	---:	---:	---:	---
4.75 cm/s	1⅞ ips	historically NAB reel: 3180 µs + 90 µs ; in later IEC/DIN standards, more commonly 3180 µs + 120 µs	formally, CCIR does not apply to this speed	a speed atypical for Hi-Fi reel-to-reel recorders; cassette standards were often adopted
9.5 cm/s	3¾ ips	3180 µs + 90 µs	formally no ‘CCIR studio’; effectively present in IEC/NAB: 3180 µs + 90 µs	In older DIN/IEC standards, other values were used, e.g. 120, 140, 200 µs
19 cm/s	7½ ips	3180 µs + 50 µs	∞ + 70 µs	this is where the real choice between NAB and CCIR begins
38 cm/s	15 ips	3180 µs + 50 µs	∞ + 35 µs	typical studio speed

In the notation ‘3180 µs + 50 µs’, the first value is the low-frequency constant and the second is the high-frequency constant. The symbol ∞ indicates the absence of a low-frequency cut-off in the given standard. MRL also explains that CCIR has been administratively taken over by the IEC and, in practice, corresponds to IEC 1, whilst NAB corresponds to IEC 2; CCIR/IEC 1 is primarily relevant to 7.5 and 15 ips, i.e. approximately 19 and 38 cm/s. ( canford.de )

---

‘Chrome’ tape in reel-to-reel recorders — an important distinction

If by ‘chrome’ you mean Type II CrO₂ / chrome equivalent cassette tape , then for a speed of 4.75 cm/s the cassette standard is:

Format	Tape	Time constants
Compact Cassette	Type I, iron	3180 µs + 120 µs
Compact Cassette	Type II/IV, chrome/metal	3180 µs + 70 µs

IASA specifies a value of 3180/120 µs for IEC Type I cassettes, and 3180/70 µs for Type II and IV cassettes. ( iasa-web.org )

In open-reel systems, however, the equivalent of ‘chrome’ was more likely to be EE — Extra Efficiency tape, e.g. Maxell XLII open-reel, TDK SA open-reel. This was not as widespread or uniform a standard as the IEC I/II cassette standards. For example, the TEAC X-1000R had the following specifications for LH tapes: 19 cm/s 3180 + 50 µs , 9.5 cm/s 3180 + 90 µs , and for EE tapes: 19 cm/s 3180 + 35 µs , 9.5 cm/s 3180 + 50 µs . ( library.mikesservers.com )

Therefore, for the ‘chrome/EE’ spool, the following approximate values can be used:

Speed	Typical Fe/LH tape, NAB	EE/chrome-equivalent tape — a common practice in consumer equipment
---:	---:	---:
4.75 cm/s	3180 + 90 µs according to the old NAB reel standard, or 3180 + 120 µs according to later IEC/DIN/cassette practice	no uniform reel standard; for the Type II cassette approach: 3180 + 70 µs
9.5 cm/s	3180 + 90 µs	frequently 3180 + 50 µs
19 cm/s	3180 + 50 µs	often 3180 + 35 µs
38 cm/s	NAB: 3180 + 50 µs , CCIR: ∞ + 35 µs	no universal EE standard; in practice, 35 µs for high frequencies is already considered a ‘fast’ value, in accordance with CCIR/IEC1 for 38 cm/s

Richard Hess points out that TEAC’s EE solutions were, in fact, additional manufacturer-specific corrections: 35 µs at 15 ips, 35 µs at 7.5 ips and 50 µs at 3.75 ips, rather than the classic, widely used tape-swap standard. ( richardhess.com )

---

A detailed analysis of the problem

1. NAB versus CCIR/IEC — what is the real difference?

For speeds 19 cm/s and 38 cm/s the difference is significant:

Speed	NAB / IEC2	CCIR / IEC1
---:	---:	---:
19 cm/s	3180 + 50 µs	∞ + 70 µs
38 cm/s	3180 + 50 µs	∞ + 35 µs

NAB maintains a constant 3180 µs , i.e. a dip around 50 Hz, whereas CCIR/IEC1 does not exhibit this dip at these speeds. IASA specifies for 38 cm/s IEC1/CCIR ∞ + 35 µs , for 38 cm/s NAB 3180 + 50 µs , for 19 cm/s IEC1/CCIR ∞ + 70 µs , and for 19 cm/s IEC2/NAB 3180 + 50 µs . ( iasa-web.org )

In listening practice:

- a tape recorded in NAB , played back as CCIR , may sound different at the lower and upper ends of the frequency range;
- a tape recorded in CCIR , when played back as NAB , will usually have an incorrect tonal balance;
- which is why studio and higher-end prosumer equipment featured NAB/IEC/CCIR selector switches.

2. What about 9.5 cm/s?

For 9.5 cm/s current practice is much simpler: the typical value is 3180 + 90 µs . The MRL states that at 3.75 ips, i.e. 9.5 cm/s, the correction currently in use is identified as NAB and IEC, with crossover frequencies of 50 Hz and 1800 Hz, i.e. approx. 3150/3180 µs + 90 µs . ( canford.de )

It is worth bearing in mind, however, that historically there were other specifications: IASA lists, for example, DIN 3180/120 µs, the earlier IEC 3180/140 µs and the older Ampex 3180/200 µs for 9.5 cm/s. For a new design, I wouldn’t complicate matters unless you want to play back archive tapes with specific documentation. ( iasa-web.org )

3. What about 4.75 cm/s?

You need to be careful here, because 4.75 cm/s is the standard speed for Compact Cassettes , not for good Hi-Fi reel-to-reel tape recorders. The old NAB reel-to-reel standard from 1965 specifies 3180 + 90 µs . ( worldradiohistory.com )

In contrast, the later IEC/DIN practice for 4.75 cm/s and the Type I cassette standard use 3180 + 120 µs , whilst cassette type II/IV uses 3180 + 70 µs . ( iasa-web.org )

Therefore, if you are building a track in a reel-to-reel system at a speed of 4.75 cm/s, it is worth allowing for the following switchable values:

- 120 µs — compliant with cassette/IEC Type I, suitable for iron-based tapes at such a low speed;
- 70 µs — if you wish to experiment with high-coercivity/chrome/EE tape;
- 90 µs — if you want to ensure compatibility with the old NAB reel.

4. Converting time constants to frequencies

Formula:

$$ f=\frac{1}{2\pi\tau} $$

Time constant	Frequency of refraction
---:	---:
3180 µs	approx. 50 Hz
120 µs	approx. 1326 Hz
90 µs	approx. 1768 Hz
70 µs	approx. 2274 Hz
50 µs	approx. 3183 Hz
35 µs	approx. 4547 Hz
17.5 µs	approx. 9095 Hz

Practical note: in some tables you will find 3150 µs instead of 3180 µs , as some standards are derived directly from the 50 Hz frequency. In tape recorder practice, 3180 µs is often used; the difference is small and is usually lost within component tolerances and track adjustment.

---

Design guidelines for your own tape recorder

If you are designing your own read/write head, this is how I would go about it:

For iron/LH tapes

Switchable reading corrections:

- 4.75 cm/s: 3180/120 µs and, optionally, 3180/90 µs;
- 9.5 cm/s: 3180/90 µs;
- 19 cm/s: NAB 3180/50 µs and CCIR ∞/70 µs;
- 38 cm/s: NAB 3180/50 µs and CCIR ∞/35 µs.

For EE/chrome-equivalent tapes

I wouldn’t call this ‘CCIR/NAB chrome’, but rather a separate entry EE :

- 9.5 cm/s EE: 3180/50 µs;
- 19 cm/s EE: 3180/35 µs;
- 4.75 cm/s chrome/Type II (experimental): 3180/70 µs;
- 38 cm/s EE: no need and no widely accepted standard; if anything, treat each case individually according to the tape and calibration.

In addition, you must switch/adjust the following separately:

- the background current,
- the recording level,
- the recording correction,
- the erase current,
- the reference level, e.g. 185/250/320 nWb/m depending on the calibration used.

Simply changing the read time constants is not enough. Without a reference tape and recording adjustments tailored to a specific tape, the track will not be compliant with NAB, CCIR or EE.

CHOPIN66 wrote:

@ElektrodaBot Was there perhaps a standard regarding the tape tension in reel-to-reel tape recorders? Or did it depend on the manufacturer of the tape recorder?

User posts preceding the question:
```
...

Direct answer to the question

Yes and no. There used to be standards specifying measurement conditions and certain recommended tape tension ranges, but there was no single universal value such as: every 1/4-inch reel-to-reel tape recorder should have, for example, 80 g of tension . In practice, the tension values were determined by the manufacturer of the specific tape recorder and specified them in the service manual as:

- tape tension in PLAY/REC mode,
- supply side tension — *supply / holdback tension*,
- take-up side tension — *take-up tension*,
- spool braking torque,
- sometimes as a force measured by a spring balance at a specified core or spool diameter.

The IEC 60094-5 standard for audio tape measurement conditions specified for the tape 6.30 mm , i.e. a typical 1/4-inch reel-to-reel tape, the tension at the heads was 1.0 ± 0.4 N , i.e. approximately 60–140 g of force . For a 3.81 mm cassette tape, the figure given was 0.5 ± 0.2 N . However, this primarily concerned a standardised test track , rather than a requirement for every consumer tape recorder. The standard also recommended that there should be no pressure pads at the heads. ( standards.iteh.ai )

It is also very important to note that even the NAB standard, when measuring speed, emphasised that speed depends, amongst other things, on the thickness of the tape and its tension , and that the measurement should be carried out with the machine adjusted in accordance with the manufacturer’s recommendations . This clearly illustrates the philosophy of the era: standards defined compatibility and measurement methods, but the mechanics of tension were left to the designer of the specific device. ( richardhess.com )

---

Typical values for 1/4-inch tape recorders

As a rough guide for 1/4-inch reel-to-reel tape recorders, the following values can be used:

Class / operating mode	Typical order of magnitude
Playback/recording, lightweight domestic mechanisms	approx. 30–70 g force
Playback/recording, better Hi-Fi / prosumer	approx. 50–100 g force
IEC measurement conditions for 6.30 mm at the heads	1.0 ± 0.4 N , i.e. approx. 60–140 g of force
Fast, controlled winding/rewinding	often approx. 100–250 g of force , depending on the mechanism
Pressure of the roller against the capstan shaft	a separate parameter, usually significantly greater, in the order of 1–2 kg of force

By way of comparison: in the Revox A77, the service manual specifies that the tension should be measured on a spindle with a diameter of 115 mm . In PLAY mode, for the ‘high’ tension setting, it specifies 70 g and 85 g , whilst for ‘low’ 30 g and 50 g — depending on the side of the track. The same service manual also specifies the braking forces and the roller pressure separately, which is 1.5 kg , so these values must not be confused. ( manualzz.com )

In contrast, the TEAC X-1000R specifies a value of 50 ± 10 g , whilst for fast-forwarding, the adjustment range is approximately 100–120 g . It is therefore clear that even high-quality 1/4-inch tape recorders did not have a single standard tension value — the values were selected to suit the specific design of the tape path, tension arms, motors and guide geometry. ( manualzz.com )

---

A detailed analysis of the problem

1. Why was there no single value?

Because the tape tension is part of the entire mechanical system. It depends on:

- the width of the tape,
- the thickness of the base material: standard play, long play, double play, triple play,
- the base material: acetate, polyester, thin long-play tapes,
- the diameter of the reels: 13 cm, 18 cm, 26.5 cm,
- the diameter of the current reel,
- the geometry of the tape guide,
- the angle the way the heads are mounted,
- the presence or absence of pressure pads,
- the type of reel motors,
- the braking method,
- whether the tape recorder operates vertically, horizontally, or in both positions.

Therefore, for example, thin long-playing tape on a small reel requires gentler handling than thick studio tape on a large NAB metal reel.

2. Feed and take-up tension

In a reel-to-reel tape recorder, a distinction must be made between two things:

- back tension / supply tension — the braking tension on the supply reel side;
- take-up tension — tension on the take-up side, required for even winding.

In PLAY/REC mode, the linear speed should be determined by the capstan feed roller with the pressure roller , rather than the spool motors. The spool motors are only intended to ensure correct tension and even winding. If the spool motors start to ‘compete’ with the capstan, this will result in increased wow and flutter, slippage, unstable tape-to-head contact or tape stretching.

3. Why must the tension be neither too low nor too high?

Tension too low:

- the tape does not lie flat against the head,
- the high-frequency response drops,
- momentary signal dropouts and modulations occur,
- the tape may ripple on the guides,
- the winding on the take-up reel becomes loose.

Excessive tension:

- accelerates head wear,
- puts strain on the capstan and guide bearings,
- may stretch thin tapes,
- reduces the longevity of the recording,
- may cause the tape edges to curl or ripple,
- increases the risk of the tape breaking during start-up, braking or rewinding.

This is a trade-off: the tension must be sufficient to ensure good contact with the heads, but as low as possible so as not to damage the tape.

---

An important distinction: tape tension versus motor torque

If you are building your own mechanism, the most important relationship is as follows:

$$ F = \frac{M}{r} $$

where:

- $F$ — belt tension,
- $M$ — motor torque of the spool,
- $r$ — current winding radius.

This means that a constant motor torque does not result in a constant belt tension , because the winding radius is constantly changing. With a small winding radius, the same torque value will result in much greater tension than with a large winding radius.

Example:

- let’s assume the required tension is: 0.7 N ,
- winding radius: 30 mm :

$$ M = F \cdot r = 0.7 \cdot 0.03 = 0.021 \text{ Nm} $$

- coil radius: 100 mm :

$$ M = 0.7 \cdot 0.10 = 0.070 \text{ Nm} $$

This means that for the same tension, the torque must change by more than three times . That is why good reel-to-reel tape recorders used either torque motors, torque switching for small/large reels, or adjustable tension arms.

---

How can this be done correctly in the tape recorder being designed?

Minimum variant

For a simpler 1/4-inch tape recorder, the following approximate values can be used:

- in PLAY/REC mode: 50–80 g of force as a starting point,
- for very thin tape: rather 40–60 g ,
- for thicker tape and larger reels: 70–100 g ,
- fast rewinding: reduce the tension and ensure a gentle acceleration and deceleration.

These are not ‘standard’ values, but a sensible starting point for a prototype.

Better option

The best solution is to use tension arms on both sides of the belt track:

- the left arm measures the tension on the feed side,
- the right-hand arm measures the tension on the take-up side,
- the arm’s position is measured by a potentiometer, a Hall effect sensor or an optocoupler,
- the microcontroller controls the torque of the spool motor so that the arm remains in the centre position.

In such a system, the spool motor should not be controlled solely by speed. It should operate primarily as a source of controlled torque . The belt speed is to be determined by the capstan.

Variant for BLDC

For BLDC motors, a sensible configuration is:

- capstan: precise speed stabilisation, preferably with an encoder or FG,
- feed reel: adjustable braking torque,
- take-up reel: adjustable winding torque,
- tape voltage loop: slower than the capstan speed loop,
- separate profiles for PLAY, REC, FF, REW, STOP.

Torque ramps are essential during start-up and stopping. Suddenly applying full spool torque is a sure-fire way to cause the tape to jerk.

---

Does the tension depend on the speed of 4.75 / 9.5 / 19 / 38 cm/s?

Not directly. Tension is not as closely linked to speed as NAB/CCIR correction. Often, the same mechanism had similar tension values for two speeds, e.g. 9.5 and 19 cm/s. In the Revox A77, the service table relates the tension values to 3¾ and 7½ ips together, i.e. to approx. 9.5 and 19 cm/s. ( manualzz.com )

However, speed has an indirect effect:

- at higher speeds, it is more difficult to mask irregularities in tracking,
- at 38 cm/s, the demands on track stability increase,
- at 4.75 cm/s, head–tape contact is critical for high frequencies,
- during fast rewinding, acceleration, deceleration and even winding become more important.

---

Practical conclusion

If you’re asking with a view to building your own tape recorder, I wouldn’t look for a single ‘magic’ value. Instead, I’d make the following assumptions:

1. For 1/4-inch tape in PLAY/REC mode, start with approx. 0.5–0.8 N , which is roughly 50–80 g of force .
2. For thin tapes, use a lower tension.
3. For large reels and studio tapes, you can increase the tension, but do so with caution.
4. Measure the actual tension on both sides of the track.
5. Use tension arms or, at the very least, calculate the winding radius.
6. Do not control the reels solely by speed — in PLAY mode, the reels should control the line tension, not the linear speed.
7. Treat tape tension, braking torque and the pressure of the roller against the capstan as separate factors.

So, the shortest answer is: there were standard ranges and measurement conditions, but the specific tension force in a reel-to-reel tape recorder was a matter of the manufacturer’s design and adjustment for a given model .