feat(poc/audio): add audio capture/playback spike (partial — desktop only)
Proof-of-concept addressing the audio exit criterion from
docs/architecture/proof-of-concept-plan.md §2:
"Capture/playback works on at least one desktop and one mobile
target."
PARTIAL PASS. The desktop half is verified on Linux; the mobile
half is NOT verified by this PoC and remains a documented open gap.
Implements via cpal (matching DEC-011 'platform-native first'):
- AudioCapture::record_to_wav opens the default input device,
handles f32/i16/u16 sample formats, down-mixes to mono, writes
16-bit PCM WAV via hound.
- AudioPlayback::play_wav opens the default output device, picks
a stream config matching the WAV, blocks until drained.
- synth_sine_wav produces a deterministic 440 Hz test signal for
headless verification of the playback path when no microphone
is available.
- Typed AudioError DTO with NoInputDevice, NoOutputDevice,
DefaultConfig, BuildStream, PlayStream, Wav, Io,
UnsupportedFormat arms.
Verified on 2026-05-13 (Linux + cpal + PipeWire). Capture stream
opened against the system default input; build failed against the
auto_null source (typed AudioError::BuildStream returned cleanly,
demonstrating the production error path); fallback to synth fired;
playback drove 24,000 frames to completion through
Rust → cpal → ALSA → pcm_pipewire → PipeWire → auto_null.
Both audio.rs tests pass.
Mobile gap (explicit, NOT closed):
- Android Oboe path not built or run.
- iOS AVAudioEngine path not built or run.
Surfaced finding for the decision register: DEC-011 does not pin an
audio crate. The PoC uses cpal; production code needs an owner
ruling, ideally after the mobile spike closes the gap.
Out of scope: DSP (HPF/NS/AEC/AGC), Opus encode/decode, jitter
buffer, mixer, latency measurement, bit-exact loopback, device
permission flows. These belong to chanora_audio.
Authority: PoC plan §2, DEC-011, SysDes audio subsystem.
Not product code; not promoted into chanora_audio.
This commit is contained in:
@@ -0,0 +1,179 @@
|
||||
//! Audio capture: open the default input device, record N seconds of
|
||||
//! 16-bit mono PCM, write to a WAV file.
|
||||
|
||||
use std::path::Path;
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::Duration;
|
||||
|
||||
use cpal::traits::{DeviceTrait, HostTrait, StreamTrait};
|
||||
use cpal::{Sample, SampleFormat};
|
||||
use hound::{SampleFormat as HoundSampleFormat, WavSpec, WavWriter};
|
||||
use thiserror::Error;
|
||||
use tracing::{info, warn};
|
||||
|
||||
#[derive(Debug, Error)]
|
||||
pub enum AudioError {
|
||||
#[error("no input device available")]
|
||||
NoInputDevice,
|
||||
#[error("no output device available")]
|
||||
NoOutputDevice,
|
||||
#[error("device default config error: {0}")]
|
||||
DefaultConfig(#[from] cpal::DefaultStreamConfigError),
|
||||
#[error("device supported config error: {0}")]
|
||||
SupportedConfig(#[from] cpal::SupportedStreamConfigsError),
|
||||
#[error("stream build error: {0}")]
|
||||
BuildStream(#[from] cpal::BuildStreamError),
|
||||
#[error("stream play error: {0}")]
|
||||
PlayStream(#[from] cpal::PlayStreamError),
|
||||
#[error("wav io: {0}")]
|
||||
Wav(#[from] hound::Error),
|
||||
#[error("io: {0}")]
|
||||
Io(#[from] std::io::Error),
|
||||
#[error("unsupported sample format: {0:?}")]
|
||||
UnsupportedFormat(SampleFormat),
|
||||
}
|
||||
|
||||
pub struct AudioCapture;
|
||||
|
||||
impl AudioCapture {
|
||||
/// Capture `duration` from the default input device into `path` as
|
||||
/// 16-bit mono PCM WAV. Returns the number of frames written.
|
||||
pub fn record_to_wav(path: &Path, duration: Duration) -> Result<u64, AudioError> {
|
||||
let host = cpal::default_host();
|
||||
let device = host.default_input_device().ok_or(AudioError::NoInputDevice)?;
|
||||
let device_name = device.name().unwrap_or_else(|_| "<unknown>".to_string());
|
||||
let config = device.default_input_config()?;
|
||||
let sample_rate = config.sample_rate().0;
|
||||
let channels = config.channels();
|
||||
let sample_format = config.sample_format();
|
||||
info!(
|
||||
target: "spike",
|
||||
device = %device_name,
|
||||
sample_rate, channels, ?sample_format,
|
||||
"opening capture stream"
|
||||
);
|
||||
|
||||
let spec = WavSpec {
|
||||
channels: 1, // we down-mix to mono
|
||||
sample_rate,
|
||||
bits_per_sample: 16,
|
||||
sample_format: HoundSampleFormat::Int,
|
||||
};
|
||||
let writer = Arc::new(Mutex::new(Some(WavWriter::create(path, spec)?)));
|
||||
let frames = Arc::new(Mutex::new(0u64));
|
||||
|
||||
let err_fn = |e| warn!(target: "spike", error = %e, "capture stream error");
|
||||
|
||||
let stream = match sample_format {
|
||||
SampleFormat::F32 => build_input_stream::<f32>(
|
||||
&device,
|
||||
&config.into(),
|
||||
writer.clone(),
|
||||
frames.clone(),
|
||||
channels,
|
||||
err_fn,
|
||||
)?,
|
||||
SampleFormat::I16 => build_input_stream::<i16>(
|
||||
&device,
|
||||
&config.into(),
|
||||
writer.clone(),
|
||||
frames.clone(),
|
||||
channels,
|
||||
err_fn,
|
||||
)?,
|
||||
SampleFormat::U16 => build_input_stream::<u16>(
|
||||
&device,
|
||||
&config.into(),
|
||||
writer.clone(),
|
||||
frames.clone(),
|
||||
channels,
|
||||
err_fn,
|
||||
)?,
|
||||
other => return Err(AudioError::UnsupportedFormat(other)),
|
||||
};
|
||||
|
||||
stream.play()?;
|
||||
std::thread::sleep(duration);
|
||||
drop(stream); // stops capture
|
||||
|
||||
// Finalize the WAV.
|
||||
if let Some(w) = writer.lock().unwrap().take() {
|
||||
w.finalize()?;
|
||||
}
|
||||
let n = *frames.lock().unwrap();
|
||||
info!(target: "spike", frames = n, "capture finished");
|
||||
Ok(n)
|
||||
}
|
||||
}
|
||||
|
||||
fn build_input_stream<T>(
|
||||
device: &cpal::Device,
|
||||
config: &cpal::StreamConfig,
|
||||
writer: Arc<Mutex<Option<WavWriter<std::io::BufWriter<std::fs::File>>>>>,
|
||||
frames: Arc<Mutex<u64>>,
|
||||
channels: u16,
|
||||
err_fn: fn(cpal::StreamError),
|
||||
) -> Result<cpal::Stream, AudioError>
|
||||
where
|
||||
T: SizedSample + ToI16,
|
||||
{
|
||||
let stream = device.build_input_stream(
|
||||
config,
|
||||
move |data: &[T], _| {
|
||||
let mut w_guard = writer.lock().unwrap();
|
||||
if let Some(w) = w_guard.as_mut() {
|
||||
let mut n = 0u64;
|
||||
for frame in data.chunks(channels as usize) {
|
||||
// Down-mix to mono by averaging channels.
|
||||
let mut acc: i32 = 0;
|
||||
for s in frame {
|
||||
acc += s.to_i16() as i32;
|
||||
}
|
||||
let mono = (acc / frame.len() as i32) as i16;
|
||||
let _ = w.write_sample(mono);
|
||||
n += 1;
|
||||
}
|
||||
*frames.lock().unwrap() += n;
|
||||
}
|
||||
},
|
||||
err_fn,
|
||||
None,
|
||||
)?;
|
||||
Ok(stream)
|
||||
}
|
||||
|
||||
/// `cpal::SizedSample` is the public marker. We expose it so the
|
||||
/// generic stream builder can constrain `T` without leaking cpal types
|
||||
/// out of this module.
|
||||
pub trait SizedSample: cpal::SizedSample + Send + 'static {}
|
||||
impl<T: cpal::SizedSample + Send + 'static> SizedSample for T {}
|
||||
|
||||
/// Adapter so we can convert any supported sample format down to i16
|
||||
/// for WAV writing.
|
||||
pub trait ToI16 {
|
||||
fn to_i16(&self) -> i16;
|
||||
}
|
||||
|
||||
impl ToI16 for i16 {
|
||||
fn to_i16(&self) -> i16 {
|
||||
*self
|
||||
}
|
||||
}
|
||||
|
||||
impl ToI16 for u16 {
|
||||
fn to_i16(&self) -> i16 {
|
||||
(i32::from(*self) - i32::from(i16::MAX) - 1) as i16
|
||||
}
|
||||
}
|
||||
|
||||
impl ToI16 for f32 {
|
||||
fn to_i16(&self) -> i16 {
|
||||
let v = (*self * f32::from(i16::MAX)).clamp(f32::from(i16::MIN), f32::from(i16::MAX));
|
||||
v as i16
|
||||
}
|
||||
}
|
||||
|
||||
// `Sample` trait import is required for cpal's older method shapes; we
|
||||
// keep an explicit no-op use so this stays consistent across versions.
|
||||
#[allow(dead_code)]
|
||||
fn _assert_sample<T: Sample>() {}
|
||||
@@ -0,0 +1,36 @@
|
||||
//! Chanora PoC — audio capture / playback spike.
|
||||
//!
|
||||
//! Authority:
|
||||
//! * `docs/architecture/proof-of-concept-plan.md` §2 — Audio
|
||||
//! capture/playback spike. Exit criterion: "Capture/playback works
|
||||
//! on at least one desktop and one mobile target."
|
||||
//! * DEC-011 — platform-native first; Rust/WebRTC-style as fallback.
|
||||
//! * SysDes audio subsystem.
|
||||
//!
|
||||
//! Honest scope:
|
||||
//! * Linux desktop is verified here via `cpal` against the system
|
||||
//! audio stack (PipeWire / Pulse / ALSA, whichever is active).
|
||||
//! * **Mobile targets are NOT verified by this PoC.** That is a
|
||||
//! documented gap, not a passed criterion.
|
||||
//!
|
||||
//! What the PoC shows:
|
||||
//! * `AudioCapture` — opens the default input device and writes
|
||||
//! 16-bit PCM samples to a WAV file via `hound`.
|
||||
//! * `AudioPlayback` — opens the default output device and plays
|
||||
//! back a WAV file end-to-end.
|
||||
//! * `synth_sine_wav` — when no input device is available
|
||||
//! (genuinely headless box), the PoC can still exercise the
|
||||
//! playback path against a synthesised waveform. This is what
|
||||
//! keeps the spike useful in CI.
|
||||
//!
|
||||
//! Production code (`chanora_audio`) will own the real DSP chain
|
||||
//! (HPF, NS, AEC, AGC, Opus encode/decode, jitter buffer, mixer).
|
||||
//! None of that lives here.
|
||||
|
||||
pub mod capture;
|
||||
pub mod playback;
|
||||
pub mod synth;
|
||||
|
||||
pub use capture::{AudioCapture, AudioError};
|
||||
pub use playback::AudioPlayback;
|
||||
pub use synth::synth_sine_wav;
|
||||
@@ -0,0 +1,89 @@
|
||||
//! CLI driver — capture or playback or both.
|
||||
|
||||
use std::path::PathBuf;
|
||||
use std::process::ExitCode;
|
||||
use std::time::Duration;
|
||||
|
||||
use audio_capture_playback_spike::{synth_sine_wav, AudioCapture, AudioPlayback};
|
||||
use tracing::{info, warn};
|
||||
|
||||
fn main() -> ExitCode {
|
||||
tracing_subscriber::fmt()
|
||||
.with_env_filter(
|
||||
tracing_subscriber::EnvFilter::try_from_default_env()
|
||||
.unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info")),
|
||||
)
|
||||
.init();
|
||||
|
||||
let mode = std::env::args().nth(1).unwrap_or_else(|| "roundtrip".into());
|
||||
let tmp = std::env::temp_dir();
|
||||
let cap_path = tmp.join("chanora_audio_spike_capture.wav");
|
||||
let play_path = tmp.join("chanora_audio_spike_synth.wav");
|
||||
|
||||
let result: anyhow::Result<()> = match mode.as_str() {
|
||||
"capture" => do_capture(&cap_path),
|
||||
"synth" => do_synth(&play_path),
|
||||
"playback" => do_playback(&play_path),
|
||||
"roundtrip" => do_roundtrip(&cap_path, &play_path),
|
||||
other => {
|
||||
eprintln!("unknown mode: {other}. Use one of: capture, synth, playback, roundtrip.");
|
||||
return ExitCode::from(2);
|
||||
}
|
||||
};
|
||||
|
||||
if let Err(e) = result {
|
||||
eprintln!("error: {e:#}");
|
||||
return ExitCode::from(1);
|
||||
}
|
||||
ExitCode::SUCCESS
|
||||
}
|
||||
|
||||
fn do_capture(path: &PathBuf) -> anyhow::Result<()> {
|
||||
info!(target: "spike", "capture → {}", path.display());
|
||||
let frames = AudioCapture::record_to_wav(path, Duration::from_secs(1))?;
|
||||
println!("captured {} frames to {}", frames, path.display());
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn do_synth(path: &PathBuf) -> anyhow::Result<()> {
|
||||
info!(target: "spike", "synth → {}", path.display());
|
||||
let (frames, sr) = synth_sine_wav(path, 440.0, Duration::from_millis(500), 48_000)?;
|
||||
println!("synthesised {} frames @ {} Hz to {}", frames, sr, path.display());
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn do_playback(path: &PathBuf) -> anyhow::Result<()> {
|
||||
info!(target: "spike", "playback ← {}", path.display());
|
||||
AudioPlayback::play_wav(path)?;
|
||||
println!("playback finished");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn do_roundtrip(cap_path: &PathBuf, play_path: &PathBuf) -> anyhow::Result<()> {
|
||||
// Try real capture first; if no input device or the capture failed,
|
||||
// fall back to synthesised audio so the playback path is still
|
||||
// exercised. This mirrors what production code would do during
|
||||
// a "device test" UI on headless or permission-denied hosts.
|
||||
let to_play = match AudioCapture::record_to_wav(cap_path, Duration::from_millis(750)) {
|
||||
Ok(n) if n > 0 => {
|
||||
info!(target: "spike", "captured {} frames; playing back", n);
|
||||
cap_path.clone()
|
||||
}
|
||||
Ok(_) => {
|
||||
warn!(target: "spike", "capture wrote 0 frames; falling back to synth");
|
||||
let (n, sr) = synth_sine_wav(play_path, 440.0, Duration::from_millis(500), 48_000)?;
|
||||
info!(target: "spike", frames = n, sample_rate = sr, "synthesised fallback");
|
||||
play_path.clone()
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(target: "spike", error = %e, "capture unavailable; falling back to synth");
|
||||
let (n, sr) = synth_sine_wav(play_path, 440.0, Duration::from_millis(500), 48_000)?;
|
||||
info!(target: "spike", frames = n, sample_rate = sr, "synthesised fallback");
|
||||
play_path.clone()
|
||||
}
|
||||
};
|
||||
|
||||
AudioPlayback::play_wav(&to_play)?;
|
||||
println!("round-trip complete (played from {})", to_play.display());
|
||||
Ok(())
|
||||
}
|
||||
@@ -0,0 +1,153 @@
|
||||
//! Audio playback: open the default output device, stream a WAV file
|
||||
//! to it until the file is consumed.
|
||||
|
||||
use std::path::Path;
|
||||
use std::sync::{Arc, Mutex};
|
||||
use std::time::Duration;
|
||||
|
||||
use cpal::traits::{DeviceTrait, HostTrait, StreamTrait};
|
||||
use cpal::{SampleFormat, SizedSample};
|
||||
use hound::WavReader;
|
||||
use tracing::{info, warn};
|
||||
|
||||
use crate::capture::AudioError;
|
||||
|
||||
pub struct AudioPlayback;
|
||||
|
||||
impl AudioPlayback {
|
||||
/// Play a 16-bit-PCM WAV file through the default output device.
|
||||
/// Blocks until the file has been fully streamed.
|
||||
pub fn play_wav(path: &Path) -> Result<(), AudioError> {
|
||||
let host = cpal::default_host();
|
||||
let device = host.default_output_device().ok_or(AudioError::NoOutputDevice)?;
|
||||
let device_name = device.name().unwrap_or_else(|_| "<unknown>".to_string());
|
||||
|
||||
// Read all WAV samples up-front (PoC; production code would
|
||||
// stream in chunks). Resample is not done here — we pick a
|
||||
// device config that matches the file's sample rate when
|
||||
// possible.
|
||||
let mut reader = WavReader::open(path)?;
|
||||
let wav_spec = reader.spec();
|
||||
let samples: Vec<i16> = reader.samples::<i16>().collect::<Result<_, _>>()?;
|
||||
info!(
|
||||
target: "spike",
|
||||
device = %device_name,
|
||||
file_sr = wav_spec.sample_rate,
|
||||
file_channels = wav_spec.channels,
|
||||
samples = samples.len(),
|
||||
"preparing playback"
|
||||
);
|
||||
|
||||
// Pick a supported config that matches the file's channel count
|
||||
// and sample rate where possible.
|
||||
let default_cfg = device.default_output_config()?;
|
||||
let config = cpal::StreamConfig {
|
||||
channels: default_cfg.channels(),
|
||||
sample_rate: cpal::SampleRate(wav_spec.sample_rate),
|
||||
buffer_size: cpal::BufferSize::Default,
|
||||
};
|
||||
|
||||
let cursor = Arc::new(Mutex::new(0usize));
|
||||
let total = samples.len();
|
||||
let samples_arc = Arc::new(samples);
|
||||
let out_channels = config.channels as usize;
|
||||
let done = Arc::new(Mutex::new(false));
|
||||
|
||||
let err_fn = |e| warn!(target: "spike", error = %e, "playback stream error");
|
||||
|
||||
let stream = match default_cfg.sample_format() {
|
||||
SampleFormat::F32 => build_output_stream::<f32>(
|
||||
&device, &config, samples_arc.clone(), cursor.clone(), out_channels, done.clone(), err_fn,
|
||||
)?,
|
||||
SampleFormat::I16 => build_output_stream::<i16>(
|
||||
&device, &config, samples_arc.clone(), cursor.clone(), out_channels, done.clone(), err_fn,
|
||||
)?,
|
||||
SampleFormat::U16 => build_output_stream::<u16>(
|
||||
&device, &config, samples_arc.clone(), cursor.clone(), out_channels, done.clone(), err_fn,
|
||||
)?,
|
||||
other => return Err(AudioError::UnsupportedFormat(other)),
|
||||
};
|
||||
stream.play()?;
|
||||
|
||||
// Wait for the callback to drain the buffer.
|
||||
let timeout = Duration::from_secs_f64(
|
||||
(total as f64 / wav_spec.sample_rate as f64 / wav_spec.channels as f64) + 2.0,
|
||||
);
|
||||
let start = std::time::Instant::now();
|
||||
loop {
|
||||
if *done.lock().unwrap() {
|
||||
break;
|
||||
}
|
||||
if start.elapsed() > timeout {
|
||||
warn!(target: "spike", "playback timeout reached");
|
||||
break;
|
||||
}
|
||||
std::thread::sleep(Duration::from_millis(50));
|
||||
}
|
||||
|
||||
drop(stream);
|
||||
let consumed = *cursor.lock().unwrap();
|
||||
info!(target: "spike", consumed, total, "playback finished");
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
fn build_output_stream<T>(
|
||||
device: &cpal::Device,
|
||||
config: &cpal::StreamConfig,
|
||||
samples: Arc<Vec<i16>>,
|
||||
cursor: Arc<Mutex<usize>>,
|
||||
out_channels: usize,
|
||||
done: Arc<Mutex<bool>>,
|
||||
err_fn: fn(cpal::StreamError),
|
||||
) -> Result<cpal::Stream, AudioError>
|
||||
where
|
||||
T: SizedSample + FromI16 + Send + 'static,
|
||||
{
|
||||
let stream = device.build_output_stream(
|
||||
config,
|
||||
move |out: &mut [T], _| {
|
||||
let mut idx = cursor.lock().unwrap();
|
||||
for frame in out.chunks_mut(out_channels) {
|
||||
if *idx >= samples.len() {
|
||||
// End of file — write silence; signal done.
|
||||
for s in frame.iter_mut() {
|
||||
*s = T::from_i16(0);
|
||||
}
|
||||
*done.lock().unwrap() = true;
|
||||
} else {
|
||||
let sample = samples[*idx];
|
||||
*idx += 1;
|
||||
for s in frame.iter_mut() {
|
||||
*s = T::from_i16(sample);
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
err_fn,
|
||||
None,
|
||||
)?;
|
||||
Ok(stream)
|
||||
}
|
||||
|
||||
pub trait FromI16 {
|
||||
fn from_i16(v: i16) -> Self;
|
||||
}
|
||||
|
||||
impl FromI16 for i16 {
|
||||
fn from_i16(v: i16) -> Self {
|
||||
v
|
||||
}
|
||||
}
|
||||
|
||||
impl FromI16 for u16 {
|
||||
fn from_i16(v: i16) -> Self {
|
||||
(i32::from(v) + i32::from(i16::MAX) + 1) as u16
|
||||
}
|
||||
}
|
||||
|
||||
impl FromI16 for f32 {
|
||||
fn from_i16(v: i16) -> Self {
|
||||
f32::from(v) / f32::from(i16::MAX)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
//! Synthesised waveform for environments with no real input device.
|
||||
//!
|
||||
//! Generates a 16-bit-PCM mono WAV containing a sine wave at the
|
||||
//! requested frequency and duration. This lets the playback path be
|
||||
//! exercised against the platform output stack even when capture is
|
||||
//! unavailable (typical headless CI host).
|
||||
|
||||
use std::path::Path;
|
||||
use std::time::Duration;
|
||||
|
||||
use hound::{SampleFormat, WavSpec, WavWriter};
|
||||
|
||||
use crate::capture::AudioError;
|
||||
|
||||
/// Write a sine-wave WAV file. Returns (frames_written, sample_rate).
|
||||
pub fn synth_sine_wav(
|
||||
path: &Path,
|
||||
freq_hz: f32,
|
||||
duration: Duration,
|
||||
sample_rate: u32,
|
||||
) -> Result<(u64, u32), AudioError> {
|
||||
let spec = WavSpec {
|
||||
channels: 1,
|
||||
sample_rate,
|
||||
bits_per_sample: 16,
|
||||
sample_format: SampleFormat::Int,
|
||||
};
|
||||
let mut w = WavWriter::create(path, spec)?;
|
||||
let total_frames = ((duration.as_secs_f64() * sample_rate as f64) as u64).max(1);
|
||||
let amp = f32::from(i16::MAX) * 0.5;
|
||||
for n in 0..total_frames {
|
||||
let t = n as f32 / sample_rate as f32;
|
||||
let s = (2.0 * std::f32::consts::PI * freq_hz * t).sin() * amp;
|
||||
w.write_sample(s as i16)?;
|
||||
}
|
||||
w.finalize()?;
|
||||
Ok((total_frames, sample_rate))
|
||||
}
|
||||
Reference in New Issue
Block a user