Assist mic snd response elsewhere #3911
Conversation
Since you may only have a microphone, you may want to send the text returned by the Wyoming Sattelite elsewhere to be spoken (ie. anohter media plaeyer). In this example the text is sent to a HA webhook so you can do lots of further automation. An example is provided in the DOCS. This is the first, untested commit. It's likely to completely fail :-) Update synthesize with HA Shebang Clueless dev... looks elsewhere and copy pastes stuff with no idea why or if it's any good. Refactor 'run' for legibility Put the extra-args in a sensible place. Update Dockerfile Forgot to copy a directory across? Linting config.yaml Fix the linting issues. linting en.yaml fix typo in DOCS.md Refactor logging for synthesize.sh No need for all the complexities. Keep it simple. logging edits Reducing the verbosity to the essential info items. avoid leaking potentially sensitive things Ready for launch of v 1.3.1 Finishing the docs, bumping the version. Isolate to Assist Microphone Delete everything except for Assist Microphone. Update README.md Add repository.json Isolate assist_microphone Make the plugin distinguishable. Update README.md Update config.yaml bad things Nothing much of interest here... just trying something out bump to force build pipeline Update config.yaml Linting & bump version to get new build. Revert "Merge branch 'master' into assist-mic--snd-response-elsewhere" This reverts commit ff6394f, reversing changes made to 531ab26.
The previous method was not very robust. Now we use http://supervisor/network/info JSON, look for one (and only one) enabled and connected IPv4 interface.
📝 WalkthroughWalkthroughThe pull request introduces version 1.3.1 of the Assist Microphone add-on, focusing on enhancing text-to-speech functionality through webhook integration. The changes include new configuration options that allow users to send text-to-speech output to a Home Assistant webhook. A new script Changes
Sequence DiagramsequenceDiagram
participant User
participant AssistMicrophone
participant HomeAssistant
participant Webhook
User->>AssistMicrophone: Configure webhook synthesis
AssistMicrophone->>AssistMicrophone: Check synthesize_using_webhook
alt Webhook Synthesis Enabled
AssistMicrophone->>HomeAssistant: Fetch network info
HomeAssistant-->>AssistMicrophone: Return network details
AssistMicrophone->>Webhook: Send text payload
Webhook-->>AssistMicrophone: Process text-to-speech
AssistMicrophone->>User: Play synthesized audio
end
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (6)
assist_microphone/CHANGELOG.md (1)
3-5: Add more details to the changelog entry.The changelog entry could be more specific about the webhook integration feature.
## 1.3.1 -Added configuration options so that sound can be played on any media player +Added webhook integration to allow TTS output to be played on any Home Assistant media playerassist_microphone/config.yaml (1)
28-28: Consider a more descriptive webhook ID.The default webhook ID could be more descriptive of its purpose.
- webhook_id: "synthesize-assist-microphone-response" + webhook_id: "assist-microphone-tts-response"assist_microphone/translations/en.yaml (2)
47-51: Improve clarity of webhook configuration description.The description could be more specific about the purpose and behavior of the webhook integration.
- When text-to-speech text is returned send it to a webhook. + Send text-to-speech output to a Home Assistant webhook for playback on any media player.
58-59: Fix grammatical error in description.- Path to the script that will doing the heavy lifting of sending the text + Path to the script that handles sending the textassist_microphone/DOCS.md (2)
61-62: Improve clarity of webhook description.Front the goal in the instructional sentence and be more direct.
-Send text-to-speech text to a Home Assistant webhook for further processing. You can achieve this by using the webhook platform as a trigger inside an automation for example. +Use a webhook platform trigger in an automation to process text-to-speech output. This enables playback on any media player connected to Home Assistant.
94-94: Improve visibility of important requirement.-If you're using this feature, you will need to set `sound_enabled` to _true_ as well or nothing will happen. +> **Important**: Set `sound_enabled` to _true_ when using this feature, otherwise no output will be produced.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
assist_microphone/CHANGELOG.md(1 hunks)assist_microphone/DOCS.md(1 hunks)assist_microphone/Dockerfile(1 hunks)assist_microphone/config.yaml(3 hunks)assist_microphone/rootfs/etc/s6-overlay/s6-rc.d/assist_microphone/run(1 hunks)assist_microphone/scripts/synthesize.sh(1 hunks)assist_microphone/translations/en.yaml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
assist_microphone/CHANGELOG.md (6)
Pattern */**(html|markdown|md): - For instructional content in documentation, use a direct and authoritative tone. Avoid expressions of politeness such as 'may' or 'please', and ensure the goal of the instruction is fronted.
- Apply the Microsoft Style Guide to ensure documentation maintains clarity and conciseness.
- In step-by-step instructions, front the location phrase in the instructional sentence.
- In step-by-step instructions, front the 'goal' in the instructional sentence.
- In step-by-step instructions, if in doubt what to front, front the 'goal' before the location phrase in the instructional sentence.
- do not hyphenate terms like 'top-right' or 'bottom-left' with 'corner'
Pattern */**(html|markdown|md): - Use bold to mark UI strings.
- If "" are used to mark UI strings, replace them by bold.
Pattern */**(html|markdown|md): - Be brief in your replies and don't add fluff like "thank you for..." and "Please let me know if"
Pattern */**(html|markdown|md): - Use sentence-style capitalization also in headings.
Pattern */**(html|markdown|md): do not comment on HTML used for icons
Pattern */**(html|markdown|md): Avoid flagging inline HTML for embedding videos in future reviews for this repository.
assist_microphone/Dockerfile (6)
Pattern */**(html|markdown|md): - For instructional content in documentation, use a direct and authoritative tone. Avoid expressions of politeness such as 'may' or 'please', and ensure the goal of the instruction is fronted.
- Apply the Microsoft Style Guide to ensure documentation maintains clarity and conciseness.
- In step-by-step instructions, front the location phrase in the instructional sentence.
- In step-by-step instructions, front the 'goal' in the instructional sentence.
- In step-by-step instructions, if in doubt what to front, front the 'goal' before the location phrase in the instructional sentence.
- do not hyphenate terms like 'top-right' or 'bottom-left' with 'corner'
Pattern */**(html|markdown|md): - Use bold to mark UI strings.
- If "" are used to mark UI strings, replace them by bold.
Pattern */**(html|markdown|md): - Be brief in your replies and don't add fluff like "thank you for..." and "Please let me know if"
Pattern */**(html|markdown|md): - Use sentence-style capitalization also in headings.
Pattern */**(html|markdown|md): do not comment on HTML used for icons
Pattern */**(html|markdown|md): Avoid flagging inline HTML for embedding videos in future reviews for this repository.
assist_microphone/DOCS.md (6)
Pattern */**(html|markdown|md): - For instructional content in documentation, use a direct and authoritative tone. Avoid expressions of politeness such as 'may' or 'please', and ensure the goal of the instruction is fronted.
- Apply the Microsoft Style Guide to ensure documentation maintains clarity and conciseness.
- In step-by-step instructions, front the location phrase in the instructional sentence.
- In step-by-step instructions, front the 'goal' in the instructional sentence.
- In step-by-step instructions, if in doubt what to front, front the 'goal' before the location phrase in the instructional sentence.
- do not hyphenate terms like 'top-right' or 'bottom-left' with 'corner'
Pattern */**(html|markdown|md): - Use bold to mark UI strings.
- If "" are used to mark UI strings, replace them by bold.
Pattern */**(html|markdown|md): - Be brief in your replies and don't add fluff like "thank you for..." and "Please let me know if"
Pattern */**(html|markdown|md): - Use sentence-style capitalization also in headings.
Pattern */**(html|markdown|md): do not comment on HTML used for icons
Pattern */**(html|markdown|md): Avoid flagging inline HTML for embedding videos in future reviews for this repository.
assist_microphone/config.yaml (6)
Pattern */**(html|markdown|md): - For instructional content in documentation, use a direct and authoritative tone. Avoid expressions of politeness such as 'may' or 'please', and ensure the goal of the instruction is fronted.
- Apply the Microsoft Style Guide to ensure documentation maintains clarity and conciseness.
- In step-by-step instructions, front the location phrase in the instructional sentence.
- In step-by-step instructions, front the 'goal' in the instructional sentence.
- In step-by-step instructions, if in doubt what to front, front the 'goal' before the location phrase in the instructional sentence.
- do not hyphenate terms like 'top-right' or 'bottom-left' with 'corner'
Pattern */**(html|markdown|md): - Use bold to mark UI strings.
- If "" are used to mark UI strings, replace them by bold.
Pattern */**(html|markdown|md): - Be brief in your replies and don't add fluff like "thank you for..." and "Please let me know if"
Pattern */**(html|markdown|md): - Use sentence-style capitalization also in headings.
Pattern */**(html|markdown|md): do not comment on HTML used for icons
Pattern */**(html|markdown|md): Avoid flagging inline HTML for embedding videos in future reviews for this repository.
🔇 Additional comments (7)
assist_microphone/rootfs/etc/s6-overlay/s6-rc.d/assist_microphone/run (1)
16-18: LGTM! Clean implementation of webhook synthesis support.The changes correctly integrate the webhook synthesis feature by conditionally adding the synthesis command based on configuration.
assist_microphone/Dockerfile (1)
30-30: LGTM! Required addition for webhook synthesis support.The scripts directory is properly copied into the container.
assist_microphone/config.yaml (3)
2-2: LGTM! Version bump matches changelog.The version is correctly incremented for the new feature.
27-29: LGTM! Well-structured configuration for webhook synthesis.The new options are properly defined with appropriate types and default values.
42-44: LGTM! Schema properly defines new option types.The schema correctly defines the types for the new configuration options.
assist_microphone/scripts/synthesize.sh (2)
69-74:⚠️ Potential issueVerify SSL certificate when using HTTPS.
The script uses
-kflag which disables SSL certificate verification. This is not secure for production use.- webhookurl="https://${ha_ip}:8123/api/webhook/${webhook_id}" + webhookurl="https://${ha_ip}:8123/api/webhook/${webhook_id}" + curl_opts="-H 'Content-Type: application/json'" - webhookurl="http://${ha_ip}:8123/api/webhook/${webhook_id}" + webhookurl="http://${ha_ip}:8123/api/webhook/${webhook_id}" + curl_opts="-k -H 'Content-Type: application/json'"Likely invalid or redundant comment.
17-18: Enhance input validation for text processing.The current implementation doesn't validate the input size or handle empty input.
Add input validation before JSON encoding:
+# Validate input +if [ ! -t 0 ]; then + text="$(cat)" + if [ -z "$text" ]; then + bashio::log.error "No input received on stdin" + exit 1 + fi + # Limit input size to prevent memory issues + if [ ${#text} -gt 1024 ]; then + bashio::log.error "Input text exceeds maximum length of 1024 characters" + exit 1 + fi + text="$(echo "$text" | jq -R -s '.')" +else + bashio::log.error "No input received on stdin" + exit 1 +fi -# Take text on stdin and JSON-encode it -text="$(cat | jq -R -s '.')"
| response=$(curl -s -o /dev/null -w "%{http_code}" -k -X POST \ | ||
| -H "Content-Type: application/json" \ | ||
| -d "$json_payload" \ | ||
| "${webhookurl}") |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add timeout to curl request.
The curl request should have a timeout to prevent hanging.
-response=$(curl -s -o /dev/null -w "%{http_code}" -k -X POST \
+response=$(curl -s -o /dev/null -w "%{http_code}" -k -X POST \
+ --max-time 10 \
-H "Content-Type: application/json" \
-d "$json_payload" \
"${webhookurl}")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| response=$(curl -s -o /dev/null -w "%{http_code}" -k -X POST \ | |
| -H "Content-Type: application/json" \ | |
| -d "$json_payload" \ | |
| "${webhookurl}") | |
| response=$(curl -s -o /dev/null -w "%{http_code}" -k -X POST \ | |
| --max-time 10 \ | |
| -H "Content-Type: application/json" \ | |
| -d "$json_payload" \ | |
| "${webhookurl}") |
| - POST | ||
| - PUT | ||
| local_only: true | ||
| webhook_id: "synthesize-assist-microphone-response" # This must match the webhook_id in the add-on configuration |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add security warning about webhook ID.
- webhook_id: "synthesize-assist-microphone-response" # This must match the webhook_id in the add-on configuration
+ webhook_id: "synthesize-assist-microphone-response" # Use a unique, non-guessable ID for security. Must match webhook_id in add-on configuration📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| webhook_id: "synthesize-assist-microphone-response" # This must match the webhook_id in the add-on configuration | |
| webhook_id: "synthesize-assist-microphone-response" # Use a unique, non-guessable ID for security. Must match webhook_id in add-on configuration |
Hi there.
You don't always have speakers hooked up to the device Assistant Microphone is running on. This PR changes the Assistant Microphone implementation so you can send TTS text to an HA webhook. We do this by leveraging the --synthesize-command to kick off a script which calls an arbitrary webhook. From there the user can run automations to have TTS run and put out on any media player.
Summary by CodeRabbit
New Features
Documentation
Chores