Azure Speech
Convert speech to text and text to speech. Review required fields, credential setup and how this connector works in Zild.
Convert speech to text and text to speech.
Where to configure
Open Zild Admin → Integrations → Connectors, find the provider and use Configure or Edit. Enter the data from this guide, enable the connector for the workflow and save.
Required fields
These requirements are the data needed by the workflow using the connector. Generic saving may accept empty fields that are only required when an operation runs. Saving does not confirm that the provider accepts the credential.
| Field | Workflow requirement |
|---|---|
ApiKey | Provider API key. |
Url | Resource region (such as eastus) or endpoint, depending on the speech workflow. Confirm with your Zild administrator. |
How to obtain credentials
- In the Azure portal, create or open the resource for the matching service.
- Open Resource Management → Keys and Endpoint.
- Copy the key into ApiKey. Also check the resource region: workflows using SpeechConfig.FromSubscription expect a region, while FromEndpoint workflows expect an endpoint.
How it works in Zild
The connector is used for voice and transcription. Different consumers interpret Url differently; verify the configured workflow before replacing a region with an endpoint.
How to verify the configuration
After saving, use the matching workflow (query, agent, call or processing) to verify access. If it fails, check the credential, permissions and selected provider resource. For limited or legacy types, confirm availability with your administrator before use.
When editing, Zild displays protected credentials as asterisks. Preserve the masked value to keep the current credential or paste a new credential to replace it.