feat(voice): transcribe Telegram voice notes with SpeechRecognition

Add a voice message handler that downloads OGG audio, converts it to WAV via pydub/ffmpeg, and transcribes it with Google Speech Recognition (pt-BR) before feeding the text into the normal message pipeline. Also extract shared text processing into process_text_message, guard against updates without a text attribute, switch the default AI provider to openrouter with deepseek-v4-flash, and document the ffmpeg system requirement in DEPLOY.md.
2026-10-25 17:27:42 -03:00
parent 6b3b6541a7
commit 25288d2c0f
73 changed files with 139973 additions and 38 deletions
@@ -0,0 +1,34 @@
+/* ====================================================================
+ * Copyright (c) 2015 Alpha Cephei Inc. All rights
+ * reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY ALPHA CEPHEI INC. ``AS IS'' AND.
+ * ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,.
+ * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL ALPHA CEPHEI INC.
+ * NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT.
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,.
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY.
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT.
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE.
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * ====================================================================
+ *
+ */
+
+This directory contains generic US english acoustic model trained with
+latest sphinxtrain.
@@ -0,0 +1,12 @@
+-lowerf 130
+-upperf 6800
+-nfilt 25
+-transform dct
+-lifter 22
+-feat 1s_c_d_dd
+-svspec 0-12/13-25/26-38
+-agc none
+-cmn current
+-varnorm no
+-model ptm
+-cmninit 40,3,-1
@@ -0,0 +1,5 @@
+<s> SIL
+</s> SIL
+<sil> SIL
+[NOISE] +NSN+
+[SPEECH] +SPN+