OVOS Transcription Validator Plugin
A plugin for OVOS that uses an OpenAI-compatible Large Language Model (LLM) to validate transcriptions from speech-to-text (STT) before they are processed by your voice assistant.
It helps filter out garbled, nonsensical, or incomplete utterances—reducing confusion and improving the accuracy of downstream skills.
Features
- Multilingual transcription validation
- Powered by OpenAI-compatible LLMs (e.g., OpenAI API, Ollama, custom servers)
- Filters out invalid utterances before processing
- Optional feedback via error sound or dialog
- Fully configurable, with per-request overrides
How It Works
- The plugin receives an STT transcription and language code.
- A structured prompt with examples is sent to the configured OpenAI-compatible LLM API.
- The LLM responds with True (valid) or False (invalid).
- If invalid:
- The utterance is canceled.
- Optionally, a dialog prompt or error sound is triggered.
Installation
pip install ovos-transcription-validator-plugin
Configuration
Add the plugin to the utterance_transformers section of your mycroft.conf.
The plugin defaults to using https://llama.smartgic.io/v1 with qwen2.5:7b and a placeholder API key sk-xxxx.
{
"utterance_transformers": {
"ovos-transcription-validator-plugin": {
"api_url": "https://llama.smartgic.io/v1",
"api_key": "sk-xxxx",
"model": "qwen2.5:7b",
"prompt_template_system": "/path/to/system_template.txt",
"prompt_template_user": "/path/to/user_template.txt",
"error_sound": true,
"mode": "ignore"
}
}
}
Available Settings
| Key | Description | Default Value |
|---|---|---|
| api_url | The URL of your OpenAI-compatible LLM API endpoint. | https://llama.smartgic.io/v1 |
| api_key | Your API key for the LLM service. Set to null or omit if no key is required (e.g., some local Ollama setups). | sk-xxxx (placeholder) |
| model | The name of the LLM model to use (e.g., qwen2.5:7b, gpt-3.5-turbo, gemma3:1b). | qwen2.5:7b |
| prompt_template_system | (Optional) Path to a .txt file to override the default system prompt for the LLM. | (internal default) |
| prompt_template_user | (Optional) Path to a .txt file to override the default user prompt template for the LLM. | (internal default) |
| error_sound | true to play a sound on error, false to disable, or a string path to a custom sound file. | false |
| mode | reprompt to ask the user to repeat the utterance, or ignore to silently cancel the invalid input. | ignore |
| max_tokens | Maximum number of tokens for the LLM's response. | 3 |
| temperature | LLM generation temperature. Lower values (e.g., 0.0) make the output more deterministic (good for True/False responses). | 0.0 |
| top_p | LLM sampling parameter. | 0.2 |
| stop_token | A list of strings that, if encountered, will cause the LLM to stop generating further tokens. | ["\n", " "] |
| api_timeout | Timeout in seconds for the LLM API request. | 10 |
Requirements & Notes
- Requires an OpenAI-compatible LLM API endpoint to be accessible ( e.g., OpenAI API, Ollama running locally, or another custom server).
- You must have a supported model already available on your chosen LLM server.
- The plugin can adapt to different languages based on the LLM's capabilities and training.
Feedback & Contributions
Found a bug or want to contribute? PRs and issues are welcome!
Metadata
Release files for ovos-transcription-validator-plugin 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ovos-transcription-validator-plugin-0.1.0.tar.gz | 19.9 kB | Without provenance | Details for ovos-transcription-validator-plugin-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ovos_transcription_validator_plugin-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ovos_transcription_validator_plugin-0.1.0-py3-none-any.whl |
Total release size: 41.3 kB
Release files / ovos-transcription-validator-plugin-0.1.0.tar.gz
| Download URL | ovos-transcription-validator-plugin-0.1.0.tar.gz |
|---|---|
| Size | 19.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
deb9530cb2cde059041a71b55850b6a532b8a4f2d00356874703e934676dcd5a
|
|
BLAKE2b-256 checksum How to use checksums |
e45b2f960e858e20e0ff7f2fb2c115f03d75b0d2edc3d1161796bc5271e2228f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.9.23
|
Release files / ovos_transcription_validator_plugin-0.1.0-py3-none-any.whl
| Download URL | ovos_transcription_validator_plugin-0.1.0-py3-none-any.whl |
|---|---|
| Size | 21.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2897aaf140bc4caf41166b7339fe22230d9aae6db4588ed0bcab9c8b959952e0
|
|
BLAKE2b-256 checksum How to use checksums |
d04a1a65ad355843c5f6d0cac610bc220a1c2adf6075a3ecfdffba9cb7ac3170
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.9.23
|
Security for ovos-transcription-validator-plugin 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.