TPA3116D2 Gain Accuracy Validation
I want to validate gain accuracy on my TPA3116D2DAD design. The chip has four selectable gain settings set by a resistor voltage divider on the GAIN/SLV pin between GVDD and GND. R19 and R20 is the voltage divider.
For this gain setting, apply a 1kHz sine wave at 100mV RMS to one channel input, single-ended, AC-coupled. Load the output with a 4Ω resistive dummy load. Power supply at 24V on PVCC.
Measure the output voltage across the load and calculate actual gain in dB. Compare against the datasheet expected values.
Two things to flag: first, if this gain setting lands outside the ±1 dB tolerance band, that points to a resistor value or GVDD voltage problem. Second, note that the gain setting is latched during power-up and cannot be changed while the device is powered, so this gain setting needs to be simulated as a separate run with the resistors configured before the supply comes up, not switched mid-simulation.
Also confirm the input bias point. The LINP, LINN, RINP, RINN input pins are internally biased at 3V, so the AC-coupled input should be sitting on a 3V DC bias at the pin. Flag if the bias point is significantly off, that would indicate the input coupling cap is loading the internal bias network incorrectly.
Thought for 43 sec
I’ll validate the TPA3116D2 gain setting from the actual R19/R20 divider and input/output network, then record the calculated/simulated gain and bias checks in a project file.
Worked for 9 mins 8 sec
Validated. R19 = 100 kΩ to GVDD and R20 = 20 kΩ to GND selects the datasheet Master 26 dB gain state; simulated output is 1.99524 Vrms across 4 Ω for 100 mVrms input, giving 25.9999 dB, so it passes the ±1 dB band.
Input bias also passes: LINP ≈ 2.99546 V and LINN ≈ 2.99547 V, close to the expected 3 V internal bias. I recorded the full calculation, datasheet comparison, latch-behavior note, and bias check in TPA3116D2DAD Gain Accuracy Validation.
Validate other gains
Check bass coupling
Review output filter
Run schematic review
Check power handling
Refine this doc
Ask about this doc
README
High-Fidelity Class-D Audio Amplifier
A compact 50 W stereo / 100 W mono Class-D amplifier board built around the TI TPA3116D2DAD, equipped with SpeakerGuard™
Image
Table
| 3D printed | Top lid cover | Body |
|---|---|---|
 Image |  Image |  Image |
What it is?
This is a PCB-level Class-D audio amplifier design with:
- Analog stereo RCA inputs for left and right audio
- Bridge-tied speaker outputs through screw terminal blocks
- External PVCC power input through a terminal block
- LC output filtering on all four half-bridge outputs
- Snubber networks to tame switching-edge ringing
- SpeakerGuard™ DC protection — the TPA3116D2DAD monitors the output for DC faults and shuts down automatically before a DC condition can damage the connected speaker — no external relay or protection circuit needed
- Bulk and local supply capacitance around the amplifier power rail
- Bootstrap capacitors for the Class-D high-side switching stages
- Mode/configuration jumpers for gain, modulation, mute/shutdown, and mono/stereo-related behavior
- Fault / control signals broken out in the schematic for experimentation and debugging
- Mounting holes and enclosure-minded geometry so it can become a finished object, not just a bare board
At the center stage is U1: TPA3116D2DAD, a TI stereo Class-D amplifier IC. Around it are the parts that make a Class-D amp behave like an audio product instead of a noisy power switch: input coupling, output inductors, output capacitors, bootstrap caps, decoupling, snubbers, and configuration resistors/jumpers. Why TPA3116DAD? →
Why I built this?
Most audio amplifier modules you find online are black boxes. They work, but you have no idea why, and there's nowhere to go when you want to change something. I wanted the opposite of that.
This is a practical, high-power, analog-input Class-D amplifier, small enough for a desktop enclosure, capable enough to drive real passive speakers from a phone, DAC, computer, mixer, or preamp. Default configuration is 50W stereo. Push it into mono/PBTL mode and you have a single high-headroom channel when you need the extra muscle.
The design is intentionally open. Tweak the gain, rework the input network, rethink the speaker terminals, design your own thermal strategy, build your own front panel. Push it further by integrating a Bluetooth module and you have a wireless speaker. Add a microphone array with a wake-word processor and you're in Amazon Echo Dot territory — a proper voice-controlled room speaker you built yourself.
The TPA3116D2DAD is well-documented, widely available, and cheap enough. That makes it a good foundation for something you'll actually finish.
For the hardcore EE audio folks: yes, there's a block diagram. I know you physically cannot evaluate a design until you've seen at least three boxes and some arrows. 😂
Want to remix this?
The board works. Here's where I'd take it further.
- Bluetooth version — integrate a Bluetooth audio module directly on the board. No dongle, no adapter, just pair and play.
- Voice assistant version — add a microphone array and wake-word processor. A self-contained Echo Dot alternative you built and actually understand.
- Balanced input version — replace the RCA input with differential input conditioning for cleaner signal handling in noisier environments like a desk with a PC or a studio rack.
- Compact embedded version — shrink the board, edge-align the connectors, and optimize for dropping directly into a powered speaker cabinet.
Take a big leap from what's already here. That's the point.
Fork it and make it yours → Break it and learn something.
Who this is for?
This project is for people who like audio hardware enough to want to touch the circuit: builders, students, hackers, speaker tinkerers, enclosure designers, and anyone who has looked at a cheap Class-D module and thought, “I want to understand and modify that.”
It is not meant to be the final word in audiophile amplifier design. It is meant to be a strong starting point: readable, forkable, and opinionated enough to invite changes.
If you remix it, I would love to see versions with cleaner enclosure integration, different input options, more formal measurement data, better thermal characterization, or a production-friendly BOM. The fun part of this project is that the core amplifier is already capable — the remix space is everything around it.
📈 Simulation and validation
Why the TPA3116D2DAD
The TPA3116D2DAD was selected as the best overall amplifier IC choice from the evaluated candidates because it provides the most complete set of built-in device and speaker protection features among the parts compared, while also being available at low cost through JLCPCB/LCSC and mainstream distributors.
Input, Output, and Jumpers
Safety and power handling notes
How can I manufacturer this?
Work-in-progress
Project status
This is a working hardware design direction centered on Class-D amplifier topology. The schematic includes the main amplifier, analog inputs, output filtering, snubbers, configuration jumpers, power input, and speaker outputs. The next best community contribution would be clearer configuration documentation, validated mono-mode instructions, test data, and a polished enclosure build.
Fork it, label it, measure it, break it carefully, and make it louder.
Welcome 👋
Flux helps you build PCBs faster with an AI teammate!
Create your account to collaborate, stay updated, fork your own version, and get instant answers from our AI agent.