diff --git a/CHANGELOG.md b/CHANGELOG.md
index 59832a7..9d358e3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -124,10 +124,17 @@ All notable changes to Flynn are documented in this file.
 - **Gateway Server** -- `GatewayServerConfig` now accepts `channelRegistry` for
   channel status reporting; static file server supports `.mjs`, `.png`, `.ico`, `.woff2`
 - **Entry Points Refactored** -- `src/index.ts` and `src/tui.ts` now delegate to
-  the CLI module (`src/cli/index.ts`) instead of directly starting the daemon/TUI
-- **Daemon Wiring** -- CronScheduler auto-registers in the channel registry when
+  CLI module (`src/cli/index.ts`) instead of directly starting daemon/TUI
+- **Daemon Wiring** -- CronScheduler auto-registers in channel registry when
   `automation.cron` jobs are configured; channelRegistry passed to GatewayServer
 
+### Fixed
+
+- **Voice Message Failure Handling** -- Telegram voice/audio messages now send user feedback on
+  download failures instead of silently dropping. When audio transcription is not configured for
+  non-audio-capable models, a graceful error message is sent to the user instead of
+  an empty message which would cause an API crash.
+
 ## [0.1.0] - 2026-02-05
 
 ### Added
diff --git a/README.md b/README.md
index b9e4a5c..f0f9e7a 100644
--- a/README.md
+++ b/README.md
@@ -170,20 +170,37 @@ Configure a Whisper-compatible endpoint for models that don't support native aud
 
 ```yaml
 audio:
-  transcription_endpoint: "http://localhost:8080/v1/audio/transcriptions"
-  transcription_api_key: "${WHISPER_API_KEY}"    # Optional Bearer token
-  transcription_model: "whisper-1"               # Model name (default: whisper-1)
-  transcription_provider: "openai"               # Provider format: openai (default)
+  enabled: true
+  provider:
+    type: custom                            # openai, groq, ollama, llamacpp, custom
+    endpoint: "http://localhost:18801/v1/audio/transcriptions"
+    api_key: "${WHISPER_API_KEY}"            # Optional Bearer token
+    model: "whisper-1"                       # Model name (default: whisper-1)
 ```
 
 | Field | Required | Description |
 |-------|----------|-------------|
-| `transcription_endpoint` | yes | Whisper-compatible API endpoint |
-| `transcription_api_key` | no | Bearer token for authentication |
-| `transcription_model` | no | Model name sent in the request (default: `whisper-1`) |
-| `transcription_provider` | no | API format: `openai` (default) |
+| `enabled` | no | Enable audio transcription (default: `false`) |
+| `provider.type` | yes | Provider type: `openai`, `groq`, `ollama`, `llamacpp`, or `custom` |
+| `provider.endpoint` | yes | Whisper-compatible API endpoint |
+| `provider.api_key` | no | Bearer token for authentication |
+| `provider.model` | no | Model name sent in request (default: `whisper-1`) |
 
-Without an `audio` config, voice messages from non-audio-capable models are silently skipped.
+Without an `audio` config, voice messages from non-audio-capable models will display an error message to the user. For local transcription, you can run a whisper.cpp server:
+
+```bash
+# Start whisper.cpp server with OpenAI-compatible endpoint
+docker run -d \
+  --name whisper-server \
+  -p 18801:8080 \
+  ghcr.io/ggml-org/whisper.cpp:main \
+  --model /app/models/ggml-base.en.bin \
+  --host 0.0.0.0 \
+  --port 8080 \
+  --convert \
+  --language en \
+  --inference-path /v1/audio/transcriptions
+```
 
 ## Telegram Commands
 
diff --git a/config/default.yaml b/config/default.yaml
index 56f1849..1462e19 100644
--- a/config/default.yaml
+++ b/config/default.yaml
@@ -123,9 +123,18 @@ hooks:
 # Configure a Whisper-compatible endpoint for audio transcription.
 # Models that support native audio input (Gemini, OpenAI, GitHub) will
 # receive raw audio directly; others fall back to this endpoint.
-
+#
+# For local transcription with whisper.cpp:
+#   docker run -d --name whisper-server -p 18801:8080 \
+#     ghcr.io/ggml-org/whisper.cpp:main \
+#     --model /app/models/ggml-base.en.bin \
+#     --host 0.0.0.0 --port 8080 --convert --language en \
+#     --inference-path /v1/audio/transcriptions
+#
 # audio:
-#   transcription_endpoint: "http://localhost:8080/v1/audio/transcriptions"
-#   transcription_api_key: "${WHISPER_API_KEY}"
-#   transcription_model: "whisper-1"
-#   transcription_provider: "openai"
+#   enabled: true
+#   provider:
+#     type: custom                            # openai, groq, ollama, llamacpp, custom
+#     endpoint: "http://localhost:18801/v1/audio/transcriptions"
+#     api_key: "${WHISPER_API_KEY}"            # Optional Bearer token
+#     model: "whisper-1"                       # Model name (default: whisper-1)