vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(gateway-chat): resume AudioContext on user gesture (no-sound / autoplay)

Browse Source 
Browsers suspend the Web Audio AudioContext until a user gesture; speakQuotes fires on
reply-complete (no active gesture), so a suspended context played silently. Prime/resume
the context on any click or keydown (capture phase) so it's running before playback.
Server side was fine throughout (/tts + /tts/stream both 200 with valid audio).
This commit is contained in:
Vuong Hoang
2026-07-09 01:41:26 -07:00
parent 0655a37bf6
commit 033f3685f5
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/gateway-chat/conf/index.html
+6
View File
@@ -147,6 +147,12 @@ function showErr(text){ const m = addMsg('error','err'); m.body.className = 'err
// --- mOrpheus TTS: streaming-decode auto-voice of quoted text (Web Audio, low TTFA) --- // --- mOrpheus TTS: streaming-decode auto-voice of quoted text (Web Audio, low TTFA) ---
let audioCtx = null; // shared AudioContext let audioCtx = null; // shared AudioContext
let ttsGen = 0; // generation counter — a newer reply's stream supersedes older ones let ttsGen = 0; // generation counter — a newer reply's stream supersedes older ones
function primeAudio(){ // browsers suspend the AudioContext until a user gesture; resume on ANY
if (!audioCtx) audioCtx = new (window.AudioContext || window.webkitAudioContext)();
if (audioCtx.state === 'suspended') audioCtx.resume(); // interaction so async playback isn't silent
}
document.addEventListener('click', primeAudio, true);
document.addEventListener('keydown', primeAudio, true);
function extractQuotes(text){ function extractQuotes(text){
const re = /“([^”]+)”|"([^"]+)"/g; // typographic "…" or straight "…" const re = /“([^”]+)”|"([^"]+)"/g; // typographic "…" or straight "…"
const out = []; let m; const out = []; let m;
tools/gateway-chat.html
+6
View File
@@ -147,6 +147,12 @@ function showErr(text){ const m = addMsg('error','err'); m.body.className = 'err
// --- mOrpheus TTS: streaming-decode auto-voice of quoted text (Web Audio, low TTFA) --- // --- mOrpheus TTS: streaming-decode auto-voice of quoted text (Web Audio, low TTFA) ---
let audioCtx = null; // shared AudioContext let audioCtx = null; // shared AudioContext
let ttsGen = 0; // generation counter — a newer reply's stream supersedes older ones let ttsGen = 0; // generation counter — a newer reply's stream supersedes older ones
function primeAudio(){ // browsers suspend the AudioContext until a user gesture; resume on ANY
if (!audioCtx) audioCtx = new (window.AudioContext || window.webkitAudioContext)();
if (audioCtx.state === 'suspended') audioCtx.resume(); // interaction so async playback isn't silent
}
document.addEventListener('click', primeAudio, true);
document.addEventListener('keydown', primeAudio, true);
function extractQuotes(text){ function extractQuotes(text){
const re = /“([^”]+)”|"([^"]+)"/g; // typographic "…" or straight "…" const re = /“([^”]+)”|"([^"]+)"/g; // typographic "…" or straight "…"
const out = []; let m; const out = []; let m;