got compression working really well, my laptops wifi card is able to talk to the nao fairly well through the door from the hallway

@

@@ -0,0 +1,4 @@
+#!/bin/bash
+pactl set-source-volume alsa_input.pci-0000_00_1b.0.analog-stereo 32%
+#python3.11 naowalk.py --ip spike.local --port 9561 --mic-gain 9 --video-scale 3.0 
+python3.11 naowalk.py --ip 127.0.0.1 --port 9561 --mic-gain 9 --video-scale 3.0 --nao-ssh-port 2222 --media-relay 127.0.0.1:8000

README.md

@@ -0,0 +1,105 @@
+# naowalk
+
+A keyboard teleop client for the NAO robot: live video, walking, head control,
+two-way audio (hear the robot's mics, make it speak via TTS), and a YouTube
+music player that downloads a track with `yt-dlp` and plays it through the
+robot's own speakers.
+
+## Requirements
+
+**System packages** (Debian/Ubuntu names — adjust for your OS):
+
+```bash
+sudo apt install portaudio19-dev ffmpeg sshpass openssh-client
+```
+
+- `portaudio19-dev` — needed to build/install `pyaudio`
+- `ffmpeg` — needed by `yt-dlp` to extract audio to mp3
+- `sshpass` + `openssh-client` — used to `scp` downloaded tracks onto the
+  robot and to run `mkdir` over `ssh` (the script assumes the default
+  `nao`/`nao` credentials)
+
+**NAOqi Python SDK (`qi`)** — not on PyPI. Download the `pynaoqi-python`
+wheel that matches your OS/Python version from the Aldebaran/SoftBank
+Robotics developer site and install it:
+
+```bash
+pip install ./pynaoqi-*.whl
+```
+
+**Python packages:**
+
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+
+```bash
+python3 naowalk.py --ip <robot-ip> [options]
+```
+
+| Flag | Default | Description |
+|---|---|---|
+| `--ip` | `127.0.0.1` | Robot's IP address |
+| `--port` | `9559` | NAOqi port |
+| `--audio-device-index` | auto | Output device index for hearing the robot's mic on your machine |
+| `--mic-channel` | `left` | Which robot mic to stream (`left`, `right`, `front`, `rear`) — pick a working one, see Troubleshooting |
+| `--mic-gain` | `8.0` | Amplification applied to the streamed mic audio |
+| `--video-scale` | `2.0` | Display window scale (base feed is 320x240) |
+
+## Controls
+
+| Key | Action |
+|---|---|
+| `W`/`A`/`S`/`D` or arrows | Walk forward/turn/back |
+| `I`/`K`/`J`/`L` | Head pitch/yaw |
+| `Space` | Reset head to center |
+| `1` | Wave gesture |
+| `M` | Open music search (type query, `Enter` to search, `↑↓` to select, `Enter`/`1`-`5` to play) |
+| `P` | Pause / resume music (resume restarts the track from the beginning — see Notes) |
+| `X` | Stop music |
+| `-` / `=` | Volume down/up |
+| `T` | Type a message for the robot to speak (TTS) |
+| `Esc` | Quit (or cancel current mode) |
+
+## How it works
+
+- **`SoundReceiver`** — registered as a NAOqi service that receives the
+  robot's mic stream and plays it out your local speakers via `pyaudio`, with
+  gain and a prebuffer to smooth out network jitter.
+- **`NaoMusicPlayer`** — searches YouTube with `yt-dlp`, downloads and
+  converts the top match to mp3, `scp`s it to the robot, and plays it with
+  `ALAudioPlayer`.
+- **`NaoTeleop`** — the main loop: pygame window for video/input, keyboard
+  handling, head/walk control, and wiring everything above together.
+
+## Notes / design decisions
+
+- **No seek.** Seeking was removed entirely — it added the most complexity
+  for the least-used feature. `P` is a simple play/stop toggle; resuming
+  restarts the track from the beginning rather than tracking a playback
+  position.
+- **`moveInit()` on startup.** The robot used to need its walk buttons
+  jittered for a few seconds before its first walk would work. `run()` now
+  calls `ALMotionProxy::moveInit()` once at startup, which settles the walk
+  engine into the right pose before any real move command — this is the
+  documented NAOqi fix for exactly this symptom.
+- **`_safe()` helper.** Most one-off NAOqi calls (setting angles, volume,
+  stopping movement, unsubscribing services) are wrapped in a small
+  `self._safe(label, fn)` helper instead of a repeated `try/except` block, so
+  one failed call logs and moves on without crashing the teleop loop or the
+  shutdown sequence.
+
+## Troubleshooting
+
+- **Mic sounds dead / silent on one channel:** some robots have one or more
+  physical mics that produce no signal. Test all four with a quick energy
+  check, then pick a working channel with `--mic-channel`.
+- **Robot falls over on the very first walk command:** make sure you're on a
+  build that includes the `moveInit()` startup call described above; if it's
+  still happening, increase the `time.sleep(1.0)` after `goToPosture` to give
+  the posture more time to settle first.
+- **`scp`/`ssh` failures for music:** confirm the robot is reachable at
+  `--ip` and that `nao`/`nao` are still the correct credentials; the script
+  hardcodes them via `sshpass`.

chat-history/claude_refactoring-python-project-files-and-code_2026-07-16T17-38-58+0000.md

@@ -0,0 +1,41 @@
+---
+title: "Refactoring Python project files and code"
+tags: []
+author: claude
+count: 2
+exporter: 3.1.0
+date: 2026-07-16T17-38-58+0000
+url: https://claude.ai/chat/313cfd88-e6b9-4256-b155-0b389d2b86c4
+---
+
+# Refactoring Python project files and code
+
+## Table of Contents
+
+- [1: make a requirements.txt, readme.md, and also remove the seek function…](#chat-1)
+- [2: how much faster can i make it walk, can we make it adjustable during r…](#chat-2)
+
+## chat-1
+
+> make a requirements.txt, readme.md, and also remove the seek function completely and reduce the lines of code without hurting stability
+
+Now the `pause()` method — simplify to a plain stop/restart toggle (no seek, no position math):
+
+Now let's add the `_safe` helper to `NaoTeleop` and use it to collapse the repeated try/except boilerplate:
+
+Now the shutdown block — this is where `_safe` pays off the most:
+
+Good — that's stable. Now let's view the final file once more end-to-end to make sure everything reads cleanly before shipping it.
+
+This looks clean and correct. Now let's write the `requirements.txt` and `README.md`.
+
+Good, all confirmed. Now the README:
+
+Now let's copy everything to outputs and present the files:
+
+___
+###### [top](#table-of-contents)
+## chat-2
+
+> how much faster can i make it walk, can we make it adjustable during runtime? we might need to change its posture so its less likely to fall and more balanced for carpet
+

chat-history/claude_replacing-music-player-backend-with-yt-dlp_2026-07-16T17-20-34+0000.md

@@ -0,0 +1,56 @@
+---
+title: "Replacing music player backend with yt-dlp"
+tags: []
+author: claude
+count: 2
+exporter: 3.1.0
+date: 2026-07-16T17-20-34+0000
+url: https://claude.ai/chat/8bb5e420-7ad2-4048-be3f-95894713aff6
+---
+
+# Replacing music player backend with yt-dlp
+
+## Table of Contents
+
+- [1: lets just gut the seek function and focus on what works. we also need…](#chat-1)
+- [2: alright awesome, lets remove the start from current position also, i w…](#chat-2)
+
+## chat-1
+
+> lets just gut the seek function and focus on what works. we also need to address the robot falling over if i try to walk from standstill, but only the first time i do it. If i jitter the walk forward and back buttons for about 3 seconds to get over the initial walk issues, it can start walking without falling over. how do we fix this
+
+Both very solvable. Let's do the walk fix first since it's the more important one — confirmed via NAOqi docs: `ALMotionProxy::moveInit()` is the standard fix for exactly this. It's a one-time blocking call that initializes the walk engine and settles the robot into the right pose _before_ the first real move command, which is exactly what your button-jittering was accidentally doing by brute force. It's missing from the script entirely.
+
+Now let's gut `seek()` entirely per your request — but keep the position tracking it shares with `pause()`, since that's still needed for resume-from-position to work:
+
+Right, orphaned body left over. Let's clean that up:
+
+Now remove the comma/period key bindings that called `seek()`:
+
+Now compile-check and confirm nothing else references `seek`:
+
+Clean. Let's ship it:
+
+___
+###### [top](#table-of-contents)
+## chat-2
+
+> alright awesome, lets remove the start from current position also, i want to get the lines of code down, what can be done without compromising on the stability and functionality to simplify our code
+
+Now let's do the full pass. First, the concrete simplification you asked for — remove position tracking, revert pause/resume to restart-from-beginning:
+
+Now `pause()` becomes a plain stop/restart toggle — no position math, no `playFileFromPosition`:
+
+Now let's cut the repetitive `try/except Exception as e: print(...)` boilerplate scattered through `NaoTeleop` — same safety, less code, via one small helper:
+
+Now let's add the `_safe` helper and apply it across these repeated sites:
+
+Now the `moveInit` startup call:
+
+Now the shutdown block — this is where it pays off most:
+
+Let's check the movement block and the `T` key's `stopMove()` call too:
+
+___
+###### [top](#table-of-contents)
+

chat-history/claude_volume-display-and-audio-underrun-fixes_2026-07-15T19-21-17+0000.md

@@ -0,0 +1,78 @@
+---
+title: "Volume display and audio underrun fixes"
+tags: []
+author: claude
+count: 2
+exporter: 3.1.0
+date: 2026-07-15T19-21-17+0000
+url: https://claude.ai/chat/0c44df5d-e4f0-425d-9730-53563dd8f762
+---
+
+# Volume display and audio underrun fixes
+
+## Table of Contents
+
+- [1: The wav file had distant sounds from my coworkers yapping. I didnt get…](#chat-1)
+- [2: audio works but is too quiet, amplify it and mix it all to make it mon…](#chat-2)
+
+## chat-1
+
+> The wav file had distant sounds from my coworkers yapping. I didnt get to talk but that proves the mic does do something
+> 
+> ┌──(lucka㉿theuniverseismine)-[~/programming/py/naowalk] 
+> └─$ python3 naomictest.py --ip spike.local --port 9561 
+> [W] 1784142061.737086 18238 qi.path.sdklayout: No Application was created, trying to deduce paths 
+> ✅ Connected to spike.local 
+> 
+> === TEST 1: Mic hardware energy (all 4 mics) === 
+> Make noise near the robot's head (clap, talk right up close to it) for 10s... 
+>  t=0s  front=1.86  rear=1.76  left=22.41  right=25.90 
+>  t=1s  front=1.78  rear=1.66  left=10.84  right=12.57 
+>  t=2s  front=1.77  rear=1.75  left=12.23  right=13.08 
+>  t=3s  front=1.75  rear=1.73  left=18.84  right=19.08 
+>  t=4s  front=1.69  rear=1.78  left=18.88  right=18.45 
+>  t=5s  front=1.73  rear=1.75  left=17.76  right=19.11 
+>  t=6s  front=1.71  rear=1.79  left=15.86  right=14.67 
+>  t=7s  front=1.73  rear=1.84  left=20.97  right=21.05 
+>  t=8s  front=1.83  rear=1.72  left=14.95  right=15.82 
+>  t=9s  front=1.68  rear=1.78  left=10.71  right=12.04 
+> ⚠ Flat mic(s): front, rear. The others responded normally, which points to a fault specific to front, rear rather than the audio 
+> pipeline as a whole (that pipeline is clearly working for the others). 
+> 
+> === TEST 2: Local on-robot recording === 
+> Recording 5s directly to /home/nao/mic_test.wav on the robot itself (this bypasses the network stream and your laptop's audio sta
+> ck entirely)... 
+> Done. Pull it off and play it with: 
+>  scp nao@spike.local:/home/nao/mic_test.wav . 
+>  (then open mic_test.wav in any media player - it's 4-channel, so check all channels) 
+> If that file has clearly audible sound, the mic and robot are fine and the 
+> bug is specifically in naowalk.py's live-streaming path. 
+> 
+> === TEST 3: Robot's own speaker === 
+> Press Enter to have the robot say a test phrase out loud...hi 
+> If you heard the robot speak just now, its speaker output is fine (this is unrelated to hearing its mic on your laptop, but rules
+> out a robot-wide audio fault). 
+> 
+> Done. Report back which test(s) failed and we'll know exactly where to look.
+
+That's the smoking gun. Look at the pattern: **left and right respond strongly to noise (10–25), front and rear are dead flat (~1.7–1.9)** — every single test agrees. And the recording that had audible coworker chatter makes total sense now: it's a 4-channel file, so the left/right tracks caught that audio while front/rear stayed silent.
+
+This was never a bug in the code. `naowalk.py` was explicitly requesting the **front** mic (`setClientPreferences(..., 3, 0)` — channel 3 = FRONTCHANNEL), which happens to be one of the two dead mics on this robot. It was faithfully streaming from a mic that produces no signal.
+
+Fix: point the stream at a working mic instead — left or right. Let me make it configurable so you can pick whichever sounds better:
+
+Now add the CLI flag and pass it through:
+
+Let's verify and ship it:
+
+___
+###### [top](#table-of-contents)
+## chat-2
+
+> audio works but is too quiet, amplify it and mix it all to make it mono
+
+Now let's rewrite `SoundReceiver` to request all mics, mix down to mono skipping dead channels, and apply amplification with a soft limiter:
+
+___
+###### [top](#table-of-contents)
+

chat-history/claude_your-first-chat-with-claude_2026-07-16T20-40-30+0000.md

@@ -0,0 +1,53 @@
+---
+title: "Your first chat with Claude"
+tags: []
+author: claude
+count: 5
+exporter: 3.1.0
+date: 2026-07-16T20-40-30+0000
+url: https://claude.ai/chat/838b001f-8bf8-4539-98ec-467513fb9860
+---
+
+# Your first chat with Claude
+
+## Table of Contents
+
+- [1: add the 6 7 meme as a third gesture](#chat-1)
+- [2: kinda looks like hes flailing his arms around, isnt it just the elbows…](#chat-2)
+- [3: right motions, but the nao currently extends his arms out, then moves…](#chat-3)
+- [4: perfect, now just rotate the hands so the palm faces up, everything el…](#chat-4)
+- [5: make him tts say six seven, also remove the input delay on starting th…](#chat-5)
+
+## chat-1
+
+> add the 6 7 meme as a third gesture
+
+## chat-2
+
+> kinda looks like hes flailing his arms around, isnt it just the elbows moving in the meme? with the arms in front
+
+Now let me replace the whole method with a version where the shoulders lock the arms up in front and only the elbows do the seesaw motion.
+
+___
+###### [top](#table-of-contents)
+## chat-3
+
+> right motions, but the nao currently extends his arms out, then moves his elbows to push the forearms close to his chest. i think the rotation is wrong on the elbow
+
+That makes sense — at `ElbowYaw=0` the elbow's bend axis is oriented so flexing curls the forearm in across the body toward the chest, not up/down in place. Rotating `ElbowYaw` about 90° turns that same hinge into a front-facing "tip" instead, and I'll shrink the swing so it's a wobble, not a full extend-then-fold.
+
+___
+###### [top](#table-of-contents)
+## chat-4
+
+> perfect, now just rotate the hands so the palm faces up, everything else is perfect
+
+## chat-5
+
+> make him tts say six seven, also remove the input delay on starting the 3rd gesture
+
+`self.tts.say(...)` is a blocking call, so it was speaking first and only starting the arm motion once the phrase finished — that's the delay. Making it fire on its own thread lets the gesture start immediately while the speech plays alongside it.
+
+___
+###### [top](#table-of-contents)
+

chat-history/scripts-used.txt

@@ -0,0 +1,2 @@
+https://github.com/iikoshteruu/enhanced-grok-export
+https://github.com/revivalstack/ai-chat-exporter

nao_video_server.py

@@ -0,0 +1,327 @@
+# -*- coding: utf-8 -*-
+"""
+nao_video_server.py - RUNS ON THE ROBOT, under its own Python 2.7.
+
+Opens a qi session to NAOqi over localhost (zero network hop - it's
+the same box) and serves TWO persistent, length-framed TCP streams -
+one for compressed video (JPEG), one for compressed audio (mu-law) -
+each on its own port/connection. They used to share one connection,
+but a single big video frame mid-send could block audio behind it for
+its whole transfer time, which is a bad tradeoff for something as
+latency-sensitive as audio. Splitting them means a slow video frame
+can never delay audio.
+
+Why not HTTP: the phone tunnel only forwards specific TCP ports, so
+this still rides over TCP - but a 5-byte binary header has none of
+HTTP's chunked/multipart-boundary parsing overhead, and it's trivial
+to keep alive and reconnect on a flaky link.
+
+Why mic capture lives here now: it used to be shipped raw (16-bit PCM,
+uncompressed) straight through NAOqi's own pub/sub over the qi RPC
+session the client holds - i.e. across the tunnel, uncompressed, the
+whole time. Subscribing to ALAudioDevice locally (same zero-hop trick
+as the camera) means only mu-law-compressed bytes ever cross the
+tunnel, half the size of raw PCM.
+
+Wire format, identical on both connections (all integers big-endian,
+via `struct`):
+    1 byte   type     0x00 HELLO   0x01 VIDEO   0x02 AUDIO
+    4 bytes  length
+    N bytes  payload
+        HELLO payload: JSON, informational only
+        VIDEO payload: JPEG bytes (video connection only)
+        AUDIO payload: mu-law encoded 8-bit samples, mono (audio connection only)
+
+Under load (slow/lossy tunnel), video quality and frame rate step
+down automatically (see QUALITY_TIERS) and recover once sends are
+fast again - and since encoding is throttled to match, this also cuts
+CPU use on a congested link instead of just wasting it on frames that
+would've been discarded anyway.
+
+Needs the SDK's own env vars, since the bindings aren't on a login
+shell's default path:
+
+    export PYTHONPATH=/opt/aldebaran/lib/python2.7/site-packages
+    export LD_LIBRARY_PATH=/opt/aldebaran/lib
+    python2 nao_video_server.py
+
+Stdlib only (BaseHTTPServer/Flask are gone entirely now) plus qi,
+cv2, and numpy, which are already confirmed present on the robot.
+"""
+import collections
+import json
+import socket
+import struct
+import threading
+import time
+
+import cv2
+import numpy as np
+import qi
+
+# ---- tunables ----
+NAOQI_PORT = 9561          # local qi session port (confirmed working)
+VIDEO_PORT = 8000          # forward both of these through the phone tunnel
+AUDIO_PORT = 8001          # kept on its own connection so a slow video
+                            # frame can never block/delay audio delivery
+CAMERA_RESOLUTION = 1      # 0=kQQVGA(160x120) 1=kQVGA(320x240) 2=kVGA(640x480)
+CAMERA_COLORSPACE = 11     # kRGBColorSpace
+CAMERA_FPS = 20
+AUDIO_RATE = 16000
+AUDIO_CHANNELS = 1
+MIC_CHANNEL = 1            # 1=left 2=right 3=front 4=rear (ALAudioDevice channel index)
+AUDIO_QUEUE_MAX = 60       # chunks buffered before we start dropping the oldest
+
+# (jpeg_quality, min_seconds_between_frames) - best link first, worst last.
+# The server steps down a tier when a video send is slow, and back up
+# after a run of fast ones.
+QUALITY_TIERS = [
+    (70, 0.05),
+    (55, 0.07),
+    (40, 0.10),
+    (25, 0.15),
+]
+SLOW_SEND_THRESHOLD = 0.20        # seconds - a send this slow means congestion
+FAST_STREAK_TO_RECOVER = 30       # consecutive quick sends before stepping back up
+
+TYPE_HELLO = 0x00
+TYPE_VIDEO = 0x01
+TYPE_AUDIO = 0x02
+
+
+def encode_ulaw(pcm16):
+    """int16 numpy array -> uint8 numpy array, mu-law companded.
+    Must match decode_ulaw() in naowalk.py exactly, or the far end
+    just hears noise - keep the two in sync if you touch this."""
+    mu = 255.0
+    x = np.clip(pcm16.astype(np.float64) / 32768.0, -1.0, 1.0)
+    y = np.sign(x) * np.log1p(mu * np.abs(x)) / np.log1p(mu)
+    return (((y + 1.0) / 2.0) * 255.0).round().astype(np.uint8)
+
+
+class FrameGrabber(object):
+    """Background thread: keeps the single most recent JPEG-encoded
+    frame available, at whatever quality tier the link currently
+    supports. A stalled capture never blocks a client's read."""
+
+    def __init__(self, session):
+        self.video = session.service("ALVideoDevice")
+        self.client = self.video.subscribeCamera(
+            "MediaServer", 0, CAMERA_RESOLUTION, CAMERA_COLORSPACE, CAMERA_FPS)
+        self._lock = threading.Lock()
+        self._jpeg = None
+        self._tier = 0
+        self._fast_streak = 0
+        self._stop = threading.Event()
+        self._thread = threading.Thread(target=self._loop)
+        self._thread.daemon = True
+        self._thread.start()
+
+    def _loop(self):
+        last_encode = 0.0
+        while not self._stop.is_set():
+            try:
+                image = self.video.getImageRemote(self.client)
+                if not image or len(image) < 7:
+                    continue
+                # getImageRemote() blocks until the next camera frame is
+                # ready (~1/CAMERA_FPS), so this loop is already paced -
+                # but under a congested tier we send far less often than
+                # that, so skip the (expensive) convert+encode work for
+                # frames we're just going to overwrite unsent anyway.
+                quality, min_interval = self.quality_and_interval()
+                now = time.time()
+                if now - last_encode < min_interval:
+                    continue
+                w, h = image[0], image[1]
+                arr = np.frombuffer(bytearray(image[6]), dtype=np.uint8).reshape((h, w, 3))
+                bgr = cv2.cvtColor(arr, cv2.COLOR_RGB2BGR)
+                ok, buf = cv2.imencode(".jpg", bgr, [cv2.IMWRITE_JPEG_QUALITY, quality])
+                if ok:
+                    with self._lock:
+                        self._jpeg = buf.tobytes()
+                    last_encode = now
+            except Exception as e:
+                print("frame grab error: %s" % e)
+                time.sleep(0.2)
+
+    def quality_and_interval(self):
+        with self._lock:
+            return QUALITY_TIERS[self._tier]
+
+    def report_send_time(self, elapsed):
+        """Called by the writer thread after each video send so we can
+        adapt to how the link is actually behaving right now."""
+        with self._lock:
+            if elapsed > SLOW_SEND_THRESHOLD:
+                self._fast_streak = 0
+                if self._tier < len(QUALITY_TIERS) - 1:
+                    self._tier += 1
+                    print("link looks congested - dropping to quality tier %d" % self._tier)
+            else:
+                self._fast_streak += 1
+                if self._fast_streak >= FAST_STREAK_TO_RECOVER and self._tier > 0:
+                    self._tier -= 1
+                    self._fast_streak = 0
+                    print("link recovered - raising to quality tier %d" % self._tier)
+
+    def latest(self):
+        with self._lock:
+            return self._jpeg
+
+    def close(self):
+        self._stop.set()
+        try:
+            self.video.unsubscribe(self.client)
+        except Exception:
+            pass
+
+
+class MicGrabber(object):
+    """Subscribes to the robot's own mic locally (zero-hop, same trick
+    as FrameGrabber) and mu-law-encodes each chunk as it arrives. This
+    replaces the old design where raw PCM was pushed to the client
+    directly through NAOqi's pub/sub over the (tunneled) qi session."""
+
+    def __init__(self, session, channel=MIC_CHANNEL):
+        self.audio = session.service("ALAudioDevice")
+        self._svc_name = "MicRelay"
+        self._lock = threading.Lock()
+        self._chunks = collections.deque(maxlen=AUDIO_QUEUE_MAX)
+        session.registerService(self._svc_name, self)
+        time.sleep(0.5)  # let NAOqi's service directory propagate the
+                          # registration before ALAudioDevice looks it up
+                          # by name, or subscribe() fails to find it
+        self.audio.setClientPreferences(self._svc_name, AUDIO_RATE, channel, 0)
+        self.audio.subscribe(self._svc_name)
+
+    def processRemote(self, nbOfChannels, nbOfSamplesByChannel, timeStamp, buffer):
+        try:
+            pcm = np.frombuffer(bytes(buffer), dtype=np.int16)
+            chunk = encode_ulaw(pcm).tobytes()
+            with self._lock:
+                self._chunks.append(chunk)
+        except Exception as e:
+            print("mic encode error: %s" % e)
+
+    def pop_all(self):
+        """Drain everything queued right now, oldest first."""
+        with self._lock:
+            out = list(self._chunks)
+            self._chunks.clear()
+        return out
+
+    def close(self):
+        try:
+            self.audio.unsubscribe(self._svc_name)
+        except Exception:
+            pass
+
+
+def _send(conn, msg_type, payload):
+    conn.sendall(struct.pack(">BI", msg_type, len(payload)))
+    conn.sendall(payload)
+
+
+def serve_video(grabber, host, port):
+    """Video gets its own connection/thread - a slow sendall() here
+    (a big JPEG frame over a bad link) must never be able to delay
+    audio, which used to share this same socket and paid for it in
+    latency."""
+    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+    sock.bind((host, port))
+    sock.listen(1)
+    print("video server listening on :%d" % port)
+    while True:
+        conn, addr = sock.accept()
+        conn.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
+        conn.settimeout(5.0)
+        print("video client connected: %s" % (addr,))
+        last_jpeg = None
+        last_send = 0.0
+        try:
+            _send(conn, TYPE_HELLO, json.dumps({"stream": "video"}).encode("utf-8"))
+            while True:
+                jpeg = grabber.latest()
+                _, min_interval = grabber.quality_and_interval()
+                now = time.time()
+                if jpeg is not None and jpeg is not last_jpeg and now - last_send >= min_interval:
+                    t0 = time.time()
+                    _send(conn, TYPE_VIDEO, jpeg)
+                    grabber.report_send_time(time.time() - t0)
+                    last_jpeg = jpeg
+                    last_send = now
+                else:
+                    time.sleep(0.01)
+        except Exception as e:
+            print("video client disconnected (%s)" % e)
+        finally:
+            try:
+                conn.close()
+            except Exception:
+                pass
+
+
+def serve_audio(mic, host, port):
+    """Audio's own connection/thread. Checked eagerly (short sleep,
+    not paced like video) since gaps are far more noticeable than a
+    video frame being a beat stale."""
+    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+    sock.bind((host, port))
+    sock.listen(1)
+    print("audio server listening on :%d" % port)
+    while True:
+        conn, addr = sock.accept()
+        conn.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
+        conn.settimeout(5.0)
+        print("audio client connected: %s" % (addr,))
+        try:
+            _send(conn, TYPE_HELLO,
+                  json.dumps({"rate": AUDIO_RATE, "channels": AUDIO_CHANNELS}).encode("utf-8"))
+            while True:
+                chunks = mic.pop_all() if mic is not None else []
+                if chunks:
+                    for chunk in chunks:
+                        _send(conn, TYPE_AUDIO, chunk)
+                else:
+                    time.sleep(0.005)
+        except Exception as e:
+            print("audio client disconnected (%s)" % e)
+        finally:
+            try:
+                conn.close()
+            except Exception:
+                pass
+
+
+def main():
+    session = qi.Session()
+    session.connect("tcp://127.0.0.1:%d" % NAOQI_PORT)
+    print("connected to local NAOqi on port %d" % NAOQI_PORT)
+
+    grabber = FrameGrabber(session)
+    mic = None
+    try:
+        mic = MicGrabber(session)
+        print("mic capture ready (mu-law, %dHz)" % AUDIO_RATE)
+    except Exception as e:
+        print("mic capture unavailable (%s) - video only" % e)
+
+    video_thread = threading.Thread(target=serve_video, args=(grabber, "0.0.0.0", VIDEO_PORT))
+    video_thread.daemon = True
+    video_thread.start()
+
+    try:
+        serve_audio(mic, "0.0.0.0", AUDIO_PORT)
+    except KeyboardInterrupt:
+        pass
+    finally:
+        grabber.close()
+        if mic:
+            mic.close()
+
+
+if __name__ == "__main__":
+    main()

naomusic.py

@@ -0,0 +1,150 @@
+# naomusic.py
+# -*- encoding: UTF-8 -*-
+
+import subprocess
+import os
+import json
+import re
+import time
+import threading
+
+class NaoMusicPlayer:
+    def __init__(self, session, nao_ip, ssh_port=22):
+        self.session = session
+        self.player = session.service("ALAudioPlayer")
+        self.nao_ip = nao_ip
+        self.ssh_port = ssh_port
+        self.music_dir = "/home/nao/music"
+        self.local_path = "/tmp/song.mp3"
+        self.remote_path = f"{self.music_dir}/song.mp3"
+        try:
+            subprocess.run(["sshpass", "-p", "nao", "ssh", "-p", str(self.ssh_port),
+                             f"nao@{nao_ip}", f"mkdir -p {self.music_dir}"],
+                         stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+        except: pass
+        self.current_file = None
+        self.current_task_id = None
+        self.is_playing = False
+        self.current_title = ""
+        self.is_loading = False
+        self.load_error = None
+        self.status = ""
+        self.progress = 0.0
+
+    def search(self, query):
+        try:
+            cmd = ["yt-dlp", f"ytsearch5:{query}", "--flat-playlist", "--dump-json",
+                   "--no-warnings", "--quiet"]
+            result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
+            entries = []
+            for line in result.stdout.strip().splitlines():
+                if not line.strip():
+                    continue
+                try:
+                    data = json.loads(line)
+                except json.JSONDecodeError:
+                    continue
+                vid = data.get("id")
+                url = data.get("url")
+                if not url or not url.startswith("http"):
+                    url = f"https://www.youtube.com/watch?v={vid}" if vid else None
+                if url:
+                    entries.append({"url": url, "title": data.get("title", "Unknown")})
+            return entries
+        except Exception as e:
+            print(f"Search error: {e}")
+            return []
+
+    _DL_PROGRESS_RE = re.compile(r'\[download\]\s+([\d.]+)%')
+
+    def play(self, url, title):
+        self.stop()
+        self.current_title = title
+        self.is_loading = True
+        self.load_error = None
+        self.status = "Starting download..."
+        self.progress = 0.0
+        try:
+            if os.path.exists(self.local_path):
+                os.remove(self.local_path)
+        except: pass
+
+        try:
+            cmd = ["yt-dlp", url,
+                   "-x", "--audio-format", "mp3",
+                   "-o", self.local_path,
+                   "--no-playlist", "--no-warnings", "--newline"]
+            print(f"\n▶ yt-dlp {url}")
+            proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+                                     text=True, bufsize=1)
+            for line in proc.stdout:
+                line = line.rstrip()
+                if not line:
+                    continue
+                print(f"  [yt-dlp] {line}")
+                m = self._DL_PROGRESS_RE.search(line)
+                if m:
+                    self.progress = float(m.group(1))
+                    self.status = f"Downloading... {self.progress:.0f}%"
+                elif "ExtractAudio" in line or "Extracting audio" in line:
+                    self.status = "Converting to mp3..."
+                elif line.startswith("[download] Destination"):
+                    self.status = "Downloading..."
+            proc.wait(timeout=120)
+
+            if proc.returncode != 0 or not os.path.exists(self.local_path):
+                print(f"Download failed (exit {proc.returncode})")
+                self.load_error = "Download failed"
+                return False
+
+            size_mb = os.path.getsize(self.local_path) / (1024 * 1024)
+            print(f"▶ scp {self.local_path} -> nao@{self.nao_ip}:{self.remote_path} ({size_mb:.1f} MB)")
+            self.progress = 0.0
+            upload_start = time.time()
+            stop_ticker = threading.Event()
+
+            def ticker():
+                while not stop_ticker.is_set():
+                    elapsed = time.time() - upload_start
+                    self.status = f"Uploading to NAO ({size_mb:.1f} MB)... {elapsed:.0f}s"
+                    stop_ticker.wait(1.0)
+
+            t = threading.Thread(target=ticker, daemon=True)
+            t.start()
+            scp_result = subprocess.run(
+                ["sshpass", "-p", "nao", "scp", "-P", str(self.ssh_port),
+                 self.local_path, f"nao@{self.nao_ip}:{self.remote_path}"],
+                capture_output=True, text=True, timeout=60
+            )
+            stop_ticker.set()
+            t.join(timeout=1.0)
+            print(f"  [scp] exit {scp_result.returncode}" +
+                  (f": {scp_result.stderr.strip()}" if scp_result.stderr.strip() else ""))
+            if scp_result.returncode != 0:
+                print(f"SCP failed: {scp_result.stderr.strip()}")
+                self.load_error = "SCP failed"
+                return False
+
+            self.current_file = self.remote_path
+            self.status = "Playing"
+            self.progress = 100.0
+            self.current_task_id = self.player.playFile(self.remote_path)
+            self.is_playing = True
+            print(f"♪ Playing on NAO: {title} (task {self.current_task_id})")
+            return True
+        except Exception as e:
+            print(f"Playback error: {e}")
+            self.load_error = str(e)
+            return False
+        finally:
+            self.is_loading = False
+
+    def stop(self):
+        try:
+            self.player.stopAll()
+        except Exception as e:
+            print(f"Stop error: {e}")
+        self.is_playing = False
+        self.current_file = None
+        self.current_task_id = None
+        self.current_title = ""

naovolume.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python3
+
+import argparse
+import sys
+import qi
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Get or set a NAO robot's volume.")
+    parser.add_argument("--ip", required=True, help="NAO IP address")
+    parser.add_argument("--port", type=int, default=9559, help="NAOqi port (default: 9559)")
+    parser.add_argument(
+        "--set",
+        type=int,
+        metavar="VOLUME",
+        help="Set volume (0-100)"
+    )
+
+    args = parser.parse_args()
+
+    try:
+        session = qi.Session()
+        session.connect(f"tcp://{args.ip}:{args.port}")
+    except RuntimeError as e:
+        print(f"Failed to connect: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    audio = session.service("ALAudioDevice")
+
+    if args.set is not None:
+        volume = max(0, min(100, args.set))
+        audio.setOutputVolume(volume)
+        print(f"Volume set to {volume}%")
+
+    print(f"Current volume: {audio.getOutputVolume()}%")
+
+
+if __name__ == "__main__":
+    main()

readme.md

@@ -0,0 +1,24 @@
+# NAO Walk - Teleoperation + Music Player
+
+A full-featured Python teleoperation tool for the NAO robot with live camera feed, head control, microphone streaming to your laptop, and **music playback directly on the robot**.
+
+---
+
+## Features
+
+- **Live Camera Feed** from NAO (upscaled on PC)
+- **Keyboard Teleop** (WASD / Arrow keys)
+- **Head Control** (I J K L)
+- **Wave Gesture** (Key `1`)
+- **Live Mic Streaming** from NAO to your laptop (with adjustable gain)
+- **Music Player on NAO** — Search & play YouTube music directly through the robot's speakers
+- **TTS Chat** — Type messages for the robot to speak (`T`)
+- **Battery & Volume Display**
+
+---
+
+## Requirements
+
+### On your laptop:
+```bash
+pip install qi opencv-python numpy pygame yt-dlp

requirements.txt

@@ -1,12 +1,14 @@
-# requirements.txt for NAO Robot Teleoperation
+# Install with: pip install -r requirements.txt
+#
+# NOTE: the NAOqi Python SDK ("qi") is NOT on PyPI. It ships separately from
+# Aldebaran/SoftBank Robotics as a platform-specific wheel (pynaoqi-python*).
+# Download it from the Softbank Robotics / Aldebaran developer portal, match
+# it to your Python version/OS, and install it with:
+#   pip install ./pynaoqi-*.whl
+# See README.md for details.
 
-# Core NAOqi SDK (required - install via Aldebaran/SoftBank installer)
-# qi  # Usually installed with the NAOqi Python SDK
-
-# Python packages
-opencv-python>=4.5.0
-pygame>=2.0.0
-numpy>=1.21.0
-
-# Optional but recommended
-pillow>=9.0.0        # If you want PIL fallback for images
+opencv-python>=4.8
+numpy>=1.24
+pygame>=2.5
+pyaudio>=0.2.13
+yt-dlp>=2024.1.1

start.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+pactl set-source-volume alsa_input.pci-0000_00_1b.0.analog-stereo 32%
+#python3.11 naowalk.py --ip spike.local --port 9561 --mic-gain 9 --video-scale 3.0 
+#python3.11 naowalk.py --ip 127.0.0.1 --port 9561 --mic-gain 9 --video-scale 3.0 --nao-ssh-port 2222 --media-relay 127.0.0.1:8000
+python3.11 naowalk.py --ip spike.local --port 9561 --mic-gain 9 --video-scale 3.0 --nao-ssh-port 22 --media-relay spike.local:8000

startSSHTunnel.sh

@@ -0,0 +1 @@
+ssh -N -L 9561:192.168.0.100:9561 -L 2222:192.168.0.100:22 -L 8000:192.168.0.100:8000 root@10.196.124.46