The user asked for a faster, real app instead of Electron. The app is now a Rust crate (serenity + songbird); the GUI in M5 will be a Tauri 2 shell on the system WebView2. - Same behaviour as the Electron core: one voice channel, per-speaker PCM to the voice worker, speaking_end and speaker_leave, sentence playback with stop and cancel, transcription notice on join, slash command join/leave/stop (create-or-update), registered chat channels with live events, history and sends that never ping, worker process with a fresh token and restart backoff. - songbird 0.6.1 garbles about a third of received frames under DAVE (its decoder keeps the bytes DAVE decryption leaves at the end of the payload; a 20 ms stepped test tone showed repeats, skips and reordering, while sending was exact). songbird now only decrypts; the core reorders packets in a small window (Opus FEC for the last lost frame) and decodes them with libopus itself. - Live test on real Discord with two bots: five sentences heard (CER 0/0/0/5/12.5%), 0.71-0.90 s from end of speech to final, speech read back at 3.4%, sound gone 0.08 s after stop. The release binary uses about 16 MB of memory; a Windows build (MinGW) logs in under Wine. - Spec moved to app/src/discord_core.spec.md; architecture, decisions, roadmap and pc-features updated. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
74 lines
2.3 KiB
Rust
74 lines
2.3 KiB
Rust
//! Binary frame layout shared with the Python voice worker (`src/voice_worker/protocol.py`).
|
|
|
|
pub const KIND_AUDIO: u8 = 0x01;
|
|
pub const KIND_TTS: u8 = 0x02;
|
|
|
|
#[derive(Debug, PartialEq, Eq)]
|
|
pub struct TtsFrame {
|
|
pub id: String,
|
|
pub seq: u32,
|
|
pub pcm: Vec<u8>,
|
|
}
|
|
|
|
/// `0x01 | u8 n | speaker id | PCM16LE` in the hello "audio" format. None if the id does not fit.
|
|
pub fn encode_audio_frame(speaker: &str, pcm: &[i16]) -> Option<Vec<u8>> {
|
|
let id = speaker.as_bytes();
|
|
if id.is_empty() || id.len() > 255 {
|
|
return None;
|
|
}
|
|
let mut out = Vec::with_capacity(2 + id.len() + pcm.len() * 2);
|
|
out.push(KIND_AUDIO);
|
|
out.push(id.len() as u8);
|
|
out.extend_from_slice(id);
|
|
for s in pcm {
|
|
out.extend_from_slice(&s.to_le_bytes());
|
|
}
|
|
Some(out)
|
|
}
|
|
|
|
/// `0x02 | u8 n | request id | u32 LE seq | PCM16LE` in the hello "tts" format. None if malformed.
|
|
pub fn decode_tts_frame(frame: &[u8]) -> Option<TtsFrame> {
|
|
if frame.len() < 2 || frame[0] != KIND_TTS {
|
|
return None;
|
|
}
|
|
let n = frame[1] as usize;
|
|
let end = 2 + n;
|
|
if n == 0 || frame.len() < end + 4 {
|
|
return None;
|
|
}
|
|
let id = std::str::from_utf8(&frame[2..end]).ok()?.to_owned();
|
|
let seq = u32::from_le_bytes(frame[end..end + 4].try_into().ok()?);
|
|
Some(TtsFrame { id, seq, pcm: frame[end + 4..].to_vec() })
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn audio_frame_is_kind_id_length_id_then_pcm() {
|
|
let f = encode_audio_frame("유저", &[1, -2]).unwrap();
|
|
let id = "유저".as_bytes();
|
|
let mut want = vec![KIND_AUDIO, id.len() as u8];
|
|
want.extend_from_slice(id);
|
|
want.extend_from_slice(&[1, 0, 0xfe, 0xff]);
|
|
assert_eq!(f, want);
|
|
}
|
|
|
|
#[test]
|
|
fn ids_must_fit_in_a_byte() {
|
|
assert!(encode_audio_frame("", &[0]).is_none());
|
|
assert!(encode_audio_frame(&"x".repeat(256), &[0]).is_none());
|
|
}
|
|
|
|
#[test]
|
|
fn tts_frames_decode_and_truncated_ones_are_refused() {
|
|
let mut f = vec![KIND_TTS, 2, b'r', b'1'];
|
|
f.extend_from_slice(&7u32.to_le_bytes());
|
|
f.extend_from_slice(&[9, 9]);
|
|
assert_eq!(decode_tts_frame(&f), Some(TtsFrame { id: "r1".into(), seq: 7, pcm: vec![9, 9] }));
|
|
assert_eq!(decode_tts_frame(&f[..5]), None);
|
|
assert_eq!(decode_tts_frame(&[KIND_AUDIO, 1, b'a', 0, 0, 0, 0]), None);
|
|
}
|
|
}
|