diff --git a/bridge/bridge.py b/bridge/bridge.py
index 753e394a..c0cb62e4 100644
--- a/bridge/bridge.py
+++ b/bridge/bridge.py
@@ -14,7 +14,9 @@ class Bridge(object):
def __init__(self):
self.btype = {
"chat": const.OPENAI,
- "voice_to_text": conf().get("voice_to_text", "openai"),
+ # Empty `voice_to_text` (the default in new configs) triggers
+ # the auto-pick below — see _auto_pick_voice_to_text for order.
+ "voice_to_text": conf().get("voice_to_text") or self._auto_pick_voice_to_text(),
"text_to_voice": conf().get("text_to_voice", "google"),
"translate": conf().get("translate", "baidu"),
}
@@ -84,6 +86,46 @@ class Bridge(object):
self.chat_bots = {}
self._agent_bridge = None
+ def refresh_voice(self):
+ """Re-read voice_to_text / text_to_voice from config and drop the
+ cached voice bots so the next call picks up the new provider.
+ Used by the web console after the user edits voice settings.
+ Does NOT touch the agent_bridge / agent state.
+ """
+ new_v2t = conf().get("voice_to_text") or self._auto_pick_voice_to_text()
+ new_t2v = conf().get("text_to_voice", "google")
+ if conf().get("use_linkai") and conf().get("linkai_api_key"):
+ if not conf().get("voice_to_text") or conf().get("voice_to_text") in ["openai"]:
+ new_v2t = const.LINKAI
+ if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
+ new_t2v = const.LINKAI
+ self.btype["voice_to_text"] = new_v2t
+ self.btype["text_to_voice"] = new_t2v
+ self.bots.pop("voice_to_text", None)
+ self.bots.pop("text_to_voice", None)
+ logger.info(f"[Bridge] voice refreshed: voice_to_text={new_v2t}, text_to_voice={new_t2v}")
+
+ @staticmethod
+ def _auto_pick_voice_to_text() -> str:
+ """Pick an ASR provider by configured api keys when voice_to_text is
+ unset. Order matches the web console: openai → dashscope → zhipu →
+ linkai. Falls back to 'openai' when nothing is configured so the
+ original "missing key" error is preserved.
+ """
+ def has(k: str) -> bool:
+ v = (conf().get(k) or "").strip()
+ return v != "" and v not in ("YOUR API KEY", "YOUR_API_KEY")
+
+ for key, provider in (
+ ("open_ai_api_key", "openai"),
+ ("dashscope_api_key", "dashscope"),
+ ("zhipu_ai_api_key", "zhipu"),
+ ("linkai_api_key", "linkai"),
+ ):
+ if has(key):
+ return provider
+ return "openai"
+
# 模型对应的接口
def get_bot(self, typename):
if self.bots.get(typename) is None:
diff --git a/channel/web/chat.html b/channel/web/chat.html
index 31705d66..ba68e0f4 100644
--- a/channel/web/chat.html
+++ b/channel/web/chat.html
@@ -422,15 +422,24 @@
-
+
+
+
+
+
{
+ const elapsed = Date.now() - recordStartedAt;
+ const minMs = 350;
+ if (elapsed < minMs) {
+ // Give the recorder a moment to capture at least one chunk
+ // before we tell it to stop.
+ setTimeout(() => stop(), minMs - elapsed);
+ } else {
+ stop();
+ }
+ };
+
+ const stop = () => {
+ if (mediaRecorder && mediaRecorder.state !== 'inactive') {
+ mediaRecorder.stop();
+ }
+ };
+
+ micBtn.addEventListener('click', () => {
+ if (recording) {
+ stopWithMinDuration();
+ } else {
+ start();
+ }
+ });
+
+ setIdle();
+})();
+
// Smart auto-scroll: pause when user scrolls up, resume when near bottom
let _autoScrollEnabled = true;
const _SCROLL_THRESHOLD = 80; // px from bottom to re-enable auto-scroll
@@ -1250,6 +1449,87 @@ document.querySelectorAll('.example-card').forEach(card => {
});
});
+// Voice-message variant of sendMessage(): renders a playable audio bubble
+// with the ASR caption, then dispatches the recognised text to /message
+// through the same SSE/loading flow as a typed message.
+function sendVoiceMessage(text, audioUrl) {
+ text = (text || '').trim();
+ if (!text) return;
+
+ inputHistory.push(text);
+ historyIdx = -1;
+ historySavedDraft = '';
+
+ const ws = document.getElementById('welcome-screen');
+ const isFirstMessage = !!ws;
+ if (ws) ws.remove();
+
+ const titleInfo = isFirstMessage ? { sid: sessionId, userMsg: text } : null;
+ const timestamp = new Date();
+ addUserVoiceMessage(audioUrl, text, timestamp);
+ const loadingEl = addLoadingIndicator();
+
+ const body = {
+ session_id: sessionId,
+ message: text,
+ stream: true,
+ timestamp: timestamp.toISOString(),
+ };
+
+ const MAX_RETRIES = 2;
+ const RETRY_DELAY_MS = 1000;
+ function postWithRetry(attempt) {
+ fetch('/message', {
+ method: 'POST',
+ headers: { 'Content-Type': 'application/json' },
+ body: JSON.stringify(body)
+ })
+ .then(r => r.json())
+ .then(data => {
+ if (data.status === 'success') {
+ if (data.stream) {
+ startSSE(data.request_id, loadingEl, timestamp, titleInfo);
+ } else {
+ loadingContainers[data.request_id] = loadingEl;
+ }
+ } else {
+ loadingEl.remove();
+ addBotMessage(t('error_send'), new Date());
+ }
+ })
+ .catch(err => {
+ if (attempt < MAX_RETRIES) {
+ setTimeout(() => postWithRetry(attempt + 1), RETRY_DELAY_MS * (attempt + 1));
+ return;
+ }
+ loadingEl.remove();
+ addBotMessage(t('error_send'), new Date());
+ });
+ }
+ postWithRetry(0);
+}
+
+function addUserVoiceMessage(audioUrl, caption, timestamp) {
+ const el = document.createElement('div');
+ el.className = 'flex justify-end px-4 sm:px-6 py-3';
+ // Voice-message bubble: playable on top, ASR caption beneath.
+ // The bubble keeps the same primary tint as a normal user message so
+ // it visually slots into the conversation flow.
+ el.innerHTML = `
+
+
+
+ ${caption ? `
${escapeHtml(caption)}
` : ''}
+
+
${formatTime(timestamp)}
+