Loading the documentation…

Set up voice input

Voice input turns your speech into text in the message box. Before the microphone can record, DataMind Oda may need to prepare its recognition models on the computer, and you choose the service and language it uses. These controls live in the Voice input plugin's details, which you open from the Plugins page. How recording and dictation work is covered in Voice input.

When Oda asks you to set up voice input

Voice input is part of a plugin you switch on first; Plugins and bundles covers that.

After voice input is switched on, Oda checks the computer for speech models. If the local models are missing, a prompt appears:

The title reads Set up voice input before recording.
The body says Voice input is enabled. First use requires downloading and preparing local recognition models. Open the plugin details to review disk space, memory and time estimates before starting setup.
The buttons are Later and Go to setup.

Go to setup opens the preparation details. It does not start a download; nothing is downloaded until you press the download button there. Later closes the prompt and leaves voice input switched on, so you can prepare the models later from the plugin's details.

Until the models are ready, the microphone in the message box stays disabled, and its tooltip says Prepare recognition in the voice plugin settings first. If intact models are already on the computer, Oda skips the prompt and downloads nothing again.

Prepare the models

Open the preparation details. Choose Go to setup in the prompt, or open the Voice input plugin from Plugins and find its card.
Expand the card. It starts collapsed; expanded, it shows Preparation steps with the individual steps.
Press Download and prepare.
Follow the steps as they run: Check local resources, Prepare recognition model, Prepare voice detection model, Verify model files, and Load with the model's name.
Watch the statuses. Each step shows one of Not started, In progress, Completed, Failed or Cancelled. While the active step works, its line counts the wait, for example Waiting 5 seconds, and the download shows a progress bar with its running totals.
Wait until the summary reports that the models are ready: Local resources are prepared. Recording wakes the recognizer. for the local service, Local speech recognition is ready. while the recognizer is awake, or Cloud speech recognition is ready. with a cloud service.

Before you start, the card shows three estimates for the local model:

Disk space: about 1 GB for the models, runtime and download caches with the default model, or about 2 GB at full precision.
Memory: about the same, 1 GB or 2 GB, with the model loaded; recognition may use more.
First setup: roughly 1 to 10 minutes, depending on your network and machine.

The figures are estimates: a slow network can take longer, downloads are reused, and an idle model releases its memory by default. The card also says: Local models will be downloaded to the computer running DataMind Oda. No Python or compiler is required.

Cancel preparation stops a running preparation. It is hidden while the recognizer is waking and disabled while the cancellation itself is in progress. A cancelled preparation keeps its completed downloads: Preparation cancelled. Completed downloads are retained. If a preparation fails, Retry preparation starts it again and reuses the files that were already downloaded and verified.

Choose the service and language

The card's settings choose how Oda recognises speech:

Recognition service chooses the service that recognises your speech. A local service runs on the computer running DataMind Oda; a cloud service is reached over the internet.
Recognition language lists the languages to listen for: Detect automatically, Chinese, English, Cantonese, Japanese and Korean. The list follows the service, so changing the service can change which languages you can pick.

Your choices are saved as you set them and persist for later sessions. While the card reports Connecting to speech recognition…, the settings and preparation controls are disabled until the connection returns; the card updates by itself.

Where the audio goes depends on the service:

With the local service, the card says Audio is recognized on the computer running DataMind Oda. First setup downloads models from Hugging Face by default, so that machine must be able to access Hugging Face and its model download services. If a proxy is needed, configure it on that machine.
With a cloud service, the card says Audio will be sent to the selected cloud service., and the local model's preparation no longer applies.
Local means the computer running DataMind Oda, which can be a different computer from the one whose browser you use.

If saving a choice fails, the card shows Speech recognition failed: <message>; try the choice again. The same line appears when starting or cancelling a preparation does not go through.

When preparation fails

If the preparation stops with a failure, the card shows what happened, a short advice line for the cause, and two values:

Download source: <source> names where the models were being fetched from.
Error code: <code> names the error the download hit, when there is one.

Cause	The card shows	What to check
The download service cannot be reached	`Cannot download <resource>: connection to the download service failed.`	That the computer running DataMind Oda can reach the download source and its model download services; configure a proxy on that machine if needed, then retry.
The download address does not resolve	`Cannot download <resource>: the download address could not be resolved.`	The DNS and proxy settings of the computer running DataMind Oda, then retry.
The download times out	`The download of <resource> timed out.`	The network or proxy connection of that computer, then retry later. Verified files are kept.
The certificate check fails	`Cannot download <resource>: certificate verification failed.`	The system clock, trusted certificates and proxy settings of that computer, then retry.
The download host answers with an error	`Cannot download <resource>: the download service returned HTTP <status>.`	That the download address is available and the proxy can reach the download service, or retry later.
A file is incomplete or fails its check	`The download of <resource> is incomplete or failed verification.`	Nothing to check; retry the download. Other completed and verified files are kept.
The file cannot be saved	`Cannot save <resource>: insufficient disk space or write permission.`	Free disk space and write permission for the model directory on that computer, then retry.
Anything else	`Could not prepare <resource>.`	The network, disk space and model directory permissions of that computer, then retry.

A preparation that fails for a reason the card cannot tie to a download step is reported as Preparation failed: <message>.

Start the preparation again from the same card. If it keeps failing, contact your DataMind OS administrator and include the message, the download source and the error code.

Questions, answered

Why does Oda ask me to set up voice input?

The local recognition models are not prepared yet. Oda checks the computer after voice input is switched on and asks you to prepare the models only when they are missing; the prompt stays until they are ready. When intact models are already there, the prompt does not appear and nothing is downloaded again.

Does `Go to setup` start the download?

No. It only opens the preparation details. Nothing is downloaded until you press Download and prepare there.

What does `Later` do?

It closes the prompt and leaves voice input switched on. Prepare the models later from the voice-input details on the Plugins page; until then the microphone tells you to prepare the models first.

Where do I find the speech recognition settings?

In the Voice input plugin's details, on the Plugins page. The card there holds the preparation controls and the Recognition service and Recognition language lists, and the first-use prompt's Go to setup button takes you straight to it.

How do I know when speech recognition is ready?

The card's summary reports it: Local resources are prepared. Recording wakes the recognizer. for the local service, Local speech recognition is ready. while the recognizer is awake, or Cloud speech recognition is ready. with a cloud service.

How much space, memory and time does the setup need?

The card estimates Disk space, Memory and First setup before the download starts. For the default local model, plan for about 1 GB of disk space and about 1 GB of memory once it is loaded; a full-precision model needs about 2 GB of each. The first setup takes roughly 1 to 10 minutes, depending on your network and machine.

Do I need Python or a compiler?

No. The card says the local models are downloaded to the computer running DataMind Oda, and no Python or compiler is required.

Which recognition languages can I choose?

Detect automatically, Chinese, English, Cantonese, Japanese and Korean. The list follows the selected service, and you can change the service or language at any time; your choices persist for later sessions.

Is my voice sent to a cloud service?

It depends on the service you choose. With the local service, audio is recognised on the computer running DataMind Oda. With a cloud service, the card says Audio will be sent to the selected cloud service. Local here means the computer running DataMind Oda, which can be a different computer from the one whose browser you use.

What does `Connecting to speech recognition…` mean?

The app is not connected to the speech service, usually for a moment while it starts or reconnects. The settings and preparation controls are disabled until the connection returns, and the card updates by itself.

What should I check when a model download fails?

Read the advice line first: the card distinguishes a connection problem, a name-resolution problem, a timeout, a certificate problem, an HTTP error from the download host, an incomplete or failed file check, and not enough disk space. The table above lists what to check for each cause. If it keeps failing, contact your DataMind OS administrator and include the message, the download source and the error code.

I cancelled preparation. Will completed downloads be made again?

No. A cancelled preparation keeps what already downloaded, and Retry preparation reuses the files that were downloaded and verified. Start it again from the card.