Transcribe

Transcribe provides real-time speech-to-text, including translation for received audio. The received audio stream from your radio's network connection is decoded, downsampled to 16 kHz, and sent in 5-second chunks to a Whisper speech-to-text endpoint. Transcripts appear immediately in a pop-out window with confidence-coloured text.

No local inference is bundled — everything runs through HTTP endpoints you configure.

Opening the Transcribe Window

Open it from Tools → Transcribe. The window pops out, click start to begin transcribing received audio while a network connection to your radio is active.

Transcribe pop-out window showing a live transcript with a callsign-tagged line displayed in confidence-coloured text

How It Works

LLM Cleanup Pass

If an LLM endpoint is configured, a second pass extracts the callsign, RST, name, QTH, and comment from each transcript segment. The callsign is prepended to the displayed line — for example [EA9KB 59] — so you can see who you're working at a glance.

Transcribe pre-converts NATO phonetic words to letters before the LLM sees the text, so the LLM receives E A 9 K B instead of Echo Alpha Nine Kilo Bravo and only needs to concatenate. This is context-aware — phonetic words are only converted when they appear in a callsign-like cluster, so "I went to Italy" stays as-is.

Once a stable callsign is cached, segments that repeat it phonetically are matched locally with no LLM API call needed, eliminating most LLM calls in a typical QSO.

Configuration

Transcribe configuration tab showing fields for cloud ASR endpoint, API key, model, language hint, LLM cleanup endpoint, and confidence threshold

Open Settings → Configuration → Transcribe tab to configure the transcription endpoints.

Cloud Speech-to-Text (Whisper) Endpoint

Transcribe works with any OpenAI-compatible Whisper endpoint. The fastest free-tier option is Groq.

To use Groq:

  1. Register at console.groq.com/keys and create an API key
  2. Set the ASR endpoint to https://api.groq.com/openai
  3. Set the ASR model to whisper-large-v3
  4. Set the language hint to en
  5. Paste your Groq API key into the ASR API key field

LLM Cleanup Pass

The optional LLM cleanup pass extracts the callsign, RST, name, QTH, and comment from each transcript segment. The callsign is prepended to the displayed line — for example [EA9KB 59]. Configure one of the following:

Local Ollama (recommended — runs entirely on your machine):

  1. Install Ollama from ollama.com
  2. Run the model: ollama run llama3.1:8b
  3. Set the LLM endpoint to http://localhost:11434
  4. Set the LLM model to llama3.1:8b
  5. Paste your Ollama API key into the llm api key field

Ollama Cloud (no local hardware required):

  1. Create an account at ollama.com
  2. Set the LLM model to an available model of your choice, for example gpt-oss:20b-cloud
  3. Supply your Ollama Cloud API key in the LLM API key field

Any OpenAI-compatible chat API works as the LLM endpoint. If you prefer another provider, set the endpoint and API key accordingly.

Configuration Fields

Transcribe configuration fields
FieldDescriptionExample
ASR EndpointOpenAI-compatible Whisper base URLhttps://api.groq.com/openai
ASR API KeyAPI key for your Whisper providerYour Groq or OpenAI key
ASR ModelWhisper model namewhisper-large-v3
Language HintISO language code to guide transcriptionen
LLM EndpointOpenAI-compatible chat completion URL (optional)http://localhost:11434
LLM API KeyAPI key for the LLM providerYour LLM provider API key
LLM ModelChat model name for the cleanup passllama3.1:8b or gpt-oss:20b-cloud
Confidence ThresholdSegments below this confidence are not displayed0.15

All settings persist to your configuration file and are restored on startup.