From 4ba86894a6f6414ddf411579a6f7a23f5ca3ef9a Mon Sep 17 00:00:00 2001
From: Orkun Manap <manap@tuta.com>
Date: Mon, 23 Mar 2026 00:11:05 +0100
Subject: [PATCH] fix: move voice-bubble detection into Telegram channel to
 avoid regression in other channels

Address review feedback: keep inferMediaType returning "audio" for all
OGG files. Voice-bubble detection (SendVoice vs SendAudio) is now done
inside the Telegram channel based on filename, so other channels that
map "audio" explicitly are unaffected.
---
 pkg/agent/loop.go                        |  6 -----
 pkg/channels/telegram/telegram.go        | 33 ++++++++++++++----------
 pkg/voice/elevenlabs_transcriber.go      |  2 +-
 pkg/voice/elevenlabs_transcriber_test.go |  4 +--
 4 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/pkg/agent/loop.go b/pkg/agent/loop.go
index e5d842c6c..725d42614 100644
--- a/pkg/agent/loop.go
+++ b/pkg/agent/loop.go
@@ -1152,12 +1152,6 @@ func inferMediaType(filename, contentType string) string {
 	ct := strings.ToLower(contentType)
 	fn := strings.ToLower(filename)
 
-	// Detect voice messages: OGG files with "voice" in the filename.
-	// These are sent as Telegram voice bubbles rather than audio attachments.
-	if strings.Contains(fn, "voice") && (strings.HasSuffix(fn, ".ogg") || strings.HasSuffix(fn, ".oga")) {
-		return "voice"
-	}
-
 	if strings.HasPrefix(ct, "image/") {
 		return "image"
 	}
diff --git a/pkg/channels/telegram/telegram.go b/pkg/channels/telegram/telegram.go
index dc67e06a8..d0011d21b 100644
--- a/pkg/channels/telegram/telegram.go
+++ b/pkg/channels/telegram/telegram.go
@@ -480,22 +480,27 @@ func (c *TelegramChannel) SendMedia(ctx context.Context, msg bus.OutboundMediaMe
 				}
 				_, err = c.bot.SendDocument(ctx, docParams)
 			}
-		case "voice":
-			params := &telego.SendVoiceParams{
-				ChatID:          tu.ID(chatID),
-				MessageThreadID: threadID,
-				Voice:           telego.InputFile{File: file},
-				Caption:         part.Caption,
-			}
-			_, err = c.bot.SendVoice(ctx, params)
 		case "audio":
-			params := &telego.SendAudioParams{
-				ChatID:          tu.ID(chatID),
-				MessageThreadID: threadID,
-				Audio:           telego.InputFile{File: file},
-				Caption:         part.Caption,
+			// Send OGG files with "voice" in the filename as Telegram voice
+			// bubbles (SendVoice) instead of audio attachments (SendAudio).
+			fn := strings.ToLower(part.Filename)
+			if strings.Contains(fn, "voice") && (strings.HasSuffix(fn, ".ogg") || strings.HasSuffix(fn, ".oga")) {
+				vparams := &telego.SendVoiceParams{
+					ChatID:          tu.ID(chatID),
+					MessageThreadID: threadID,
+					Voice:           telego.InputFile{File: file},
+					Caption:         part.Caption,
+				}
+				_, err = c.bot.SendVoice(ctx, vparams)
+			} else {
+				params := &telego.SendAudioParams{
+					ChatID:          tu.ID(chatID),
+					MessageThreadID: threadID,
+					Audio:           telego.InputFile{File: file},
+					Caption:         part.Caption,
+				}
+				_, err = c.bot.SendAudio(ctx, params)
 			}
-			_, err = c.bot.SendAudio(ctx, params)
 		case "video":
 			params := &telego.SendVideoParams{
 				ChatID:          tu.ID(chatID),
diff --git a/pkg/voice/elevenlabs_transcriber.go b/pkg/voice/elevenlabs_transcriber.go
index 44f4bd88e..93db10f8d 100644
--- a/pkg/voice/elevenlabs_transcriber.go
+++ b/pkg/voice/elevenlabs_transcriber.go
@@ -87,7 +87,7 @@ func (t *ElevenLabsTranscriber) Transcribe(ctx context.Context, audioFilePath st
 	}
 
 	req.Header.Set("Content-Type", writer.FormDataContentType())
-	req.Header.Set("xi-api-key", t.apiKey)
+	req.Header.Set("Xi-Api-Key", t.apiKey)
 
 	logger.DebugCF("voice", "Sending transcription request to ElevenLabs API", map[string]any{
 		"url":                url,
diff --git a/pkg/voice/elevenlabs_transcriber_test.go b/pkg/voice/elevenlabs_transcriber_test.go
index 119282542..78be8958a 100644
--- a/pkg/voice/elevenlabs_transcriber_test.go
+++ b/pkg/voice/elevenlabs_transcriber_test.go
@@ -32,8 +32,8 @@ func TestElevenLabsTranscribe(t *testing.T) {
 			if r.URL.Path != "/v1/speech-to-text" {
 				t.Errorf("unexpected path: %s", r.URL.Path)
 			}
-			if r.Header.Get("xi-api-key") != "sk_test" {
-				t.Errorf("unexpected xi-api-key header: %s", r.Header.Get("xi-api-key"))
+			if r.Header.Get("Xi-Api-Key") != "sk_test" {
+				t.Errorf("unexpected xi-api-key header: %s", r.Header.Get("Xi-Api-Key"))
 			}
 			w.Header().Set("Content-Type", "application/json")
 			_ = json.NewEncoder(w).Encode(TranscriptionResponse{