diff --git a/README.md b/README.md
index da9e29579..4494cd4a8 100644
--- a/README.md
+++ b/README.md
@@ -143,7 +143,7 @@ Convert text to speech with three providers:
 | **ElevenLabs** | Excellent | Paid | `ELEVENLABS_API_KEY` |
 | **OpenAI TTS** | Good | Paid | `OPENAI_API_KEY` |
 
-On Telegram, audio plays as native voice bubbles. On Discord/WhatsApp, sent as audio files. In CLI mode, saved to `~/voice-memos/`.
+On Telegram, audio plays as native voice bubbles (the round, inline-playable kind). On Discord/WhatsApp, sent as audio file attachments. In CLI mode, saved to `~/voice-memos/`.
 
 **Configure in `~/.hermes/config.yaml`:**
 ```yaml
@@ -159,7 +159,22 @@ tts:
     voice: "alloy"              # alloy, echo, fable, onyx, nova, shimmer
 ```
 
-> **Note:** Telegram voice bubbles require `ffmpeg` for Opus conversion (Edge TTS only outputs MP3). Install with `apt install ffmpeg` or `brew install ffmpeg`. Without ffmpeg, audio is sent as a file instead of a voice bubble.
+**Telegram voice bubbles & ffmpeg:**
+
+Telegram voice bubbles require Opus/OGG audio format. OpenAI and ElevenLabs produce Opus natively — no extra dependencies needed. Edge TTS (the default free provider) outputs MP3 and needs **ffmpeg** to convert to Opus:
+
+```bash
+# Ubuntu/Debian
+sudo apt install ffmpeg
+
+# macOS
+brew install ffmpeg
+
+# Fedora
+sudo dnf install ffmpeg
+```
+
+Without ffmpeg, Edge TTS audio is sent as a regular audio file (playable, but shows as a rectangular player instead of a voice bubble). If you want voice bubbles without installing ffmpeg, switch to the OpenAI or ElevenLabs provider.
 
 ### 📄 Context Files (SOUL.md, AGENTS.md, .cursorrules)
 
diff --git a/docs/messaging.md b/docs/messaging.md
index fb52ed4d1..aa67cbe11 100644
--- a/docs/messaging.md
+++ b/docs/messaging.md
@@ -313,10 +313,10 @@ The `text_to_speech` tool generates audio that the gateway delivers as native vo
 
 | Platform | Delivery | Format |
 |----------|----------|--------|
-| Telegram | Voice bubble (plays inline) | Opus `.ogg` (converted from MP3 via ffmpeg) |
+| Telegram | Voice bubble (plays inline) | Opus `.ogg` — native from OpenAI/ElevenLabs, converted via ffmpeg for Edge TTS |
 | Discord | Audio file attachment | MP3 |
 | WhatsApp | Audio file attachment | MP3 |
-| CLI | Saved to `~/voice-memos/` | MP3 (or Opus if ffmpeg available) |
+| CLI | Saved to `~/voice-memos/` | MP3 |
 
 **Providers:**
 - **Edge TTS** (default) — Free, no API key, 322 voices in 74 languages
@@ -327,7 +327,17 @@ Voice and provider are configured by the user in `~/.hermes/config.yaml` under t
 
 The tool returns a `MEDIA:<path>` tag that the gateway send pipeline intercepts and delivers as a native audio message. If `[[audio_as_voice]]` is present (Opus format available), Telegram sends it as a voice bubble instead of an audio file.
 
-> **Note:** Telegram voice bubbles require `ffmpeg` for Opus conversion (Edge TTS outputs MP3). Install with `apt install ffmpeg` or `brew install ffmpeg`. Without ffmpeg, audio is sent as a regular file.
+**Telegram voice bubbles & ffmpeg:**
+
+Telegram requires Opus/OGG format for native voice bubbles (the round, inline-playable kind). **OpenAI and ElevenLabs** produce Opus natively when on Telegram — no extra setup needed. **Edge TTS** (the default free provider) outputs MP3 and needs `ffmpeg` to convert:
+
+```bash
+sudo apt install ffmpeg    # Ubuntu/Debian
+brew install ffmpeg         # macOS
+sudo dnf install ffmpeg     # Fedora
+```
+
+Without ffmpeg, Edge TTS audio is sent as a regular audio file (still playable, but shows as a rectangular music player instead of a voice bubble).
 
 ## Cron Job Delivery
 
diff --git a/gateway/run.py b/gateway/run.py
index 901f581cf..c66ce19ca 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -589,30 +589,37 @@ class GatewayRunner:
                     return f"⚠️ {result['error']}"
                 return "(No response generated)"
             
-            # Scan tool results in the conversation for MEDIA:<path> tags.
-            # The TTS tool (and potentially other media-producing tools) embed
-            # MEDIA: tags in their JSON responses, but the model's final reply
-            # typically doesn't include them -- it just says "here you go".
-            # We collect those tags and append them to the final response so
-            # the adapter's extract_media() can find and deliver the files.
-            media_tags = []
-            for msg in result.get("messages", []):
-                if msg.get("role") == "tool" or (msg.get("role") == "function"):
-                    content = msg.get("content", "")
-                    if "MEDIA:" in content:
-                        # Extract MEDIA: tags from tool result (may be inside JSON).
-                        # Strip trailing JSON artifacts like quotes and commas that
-                        # get caught by the \S+ when the tag is inside a JSON string.
-                        for match in re.finditer(r'MEDIA:(\S+)', content):
-                            path = match.group(1).strip().rstrip('",}')
-                            if path:
-                                media_tags.append(f"MEDIA:{path}")
-                        # Also capture the [[audio_as_voice]] directive
-                        if "[[audio_as_voice]]" in content:
-                            media_tags.insert(0, "[[audio_as_voice]]")
-            
-            if media_tags:
-                final_response = final_response + "\n" + "\n".join(media_tags)
+            # Scan tool results for MEDIA:<path> tags that need to be delivered
+            # as native audio/file attachments.  The TTS tool embeds MEDIA: tags
+            # in its JSON response, but the model's final text reply usually
+            # doesn't include them.  We collect unique tags from tool results and
+            # append any that aren't already present in the final response, so the
+            # adapter's extract_media() can find and deliver the files exactly once.
+            if "MEDIA:" not in final_response:
+                media_tags = []
+                has_voice_directive = False
+                for msg in result.get("messages", []):
+                    if msg.get("role") == "tool" or msg.get("role") == "function":
+                        content = msg.get("content", "")
+                        if "MEDIA:" in content:
+                            for match in re.finditer(r'MEDIA:(\S+)', content):
+                                path = match.group(1).strip().rstrip('",}')
+                                if path:
+                                    media_tags.append(f"MEDIA:{path}")
+                            if "[[audio_as_voice]]" in content:
+                                has_voice_directive = True
+                
+                if media_tags:
+                    # Deduplicate while preserving order
+                    seen = set()
+                    unique_tags = []
+                    for tag in media_tags:
+                        if tag not in seen:
+                            seen.add(tag)
+                            unique_tags.append(tag)
+                    if has_voice_directive:
+                        unique_tags.insert(0, "[[audio_as_voice]]")
+                    final_response = final_response + "\n" + "\n".join(unique_tags)
             
             return final_response
         
diff --git a/scripts/install.sh b/scripts/install.sh
index f913198c6..d6c9609f1 100755
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -423,8 +423,12 @@ check_ffmpeg() {
         return
     fi
     
-    log_warn "ffmpeg not found (TTS voice bubbles on Telegram will send as audio files instead)"
-    log_info "To install ffmpeg (optional):"
+    log_warn "ffmpeg not found"
+    log_info "ffmpeg is needed for Telegram voice bubbles when using the default Edge TTS provider."
+    log_info "Without it, Edge TTS audio is sent as a file instead of a voice bubble."
+    log_info "(OpenAI and ElevenLabs TTS produce Opus natively and don't need ffmpeg.)"
+    log_info ""
+    log_info "To install ffmpeg:"
     
     case "$OS" in
         linux)