Speechall Developer Resources

Everything needed to evaluate, integrate, and automate the Speechall unified speech-to-text API.

Speechall API documentation

Guides and examples for integrating unified speech-to-text into an application.

Speechall OpenAPI specification

The canonical machine-readable API schema, including operations, parameters, and response models.

Speechall authentication guide

Create an API key and authenticate API calls with a Bearer token.

Speechall CLI

Install the official command-line tool for scriptable transcription and model discovery.

Integration guidance for developers and agents

Start by reading the Speechall API documentation and reviewing the OpenAPI specification. The schema is served from this domain at /api/openapi.yaml and is the source of truth for REST operations, typed request parameters, authentication requirements, and API response formats. The API health check is available at https://api.speechall.com/, while production API calls use https://api.speechall.com/v1.

Speechall API authentication uses a Bearer API key created in the console. Agents and applications should first list available speech-to-text models, then select a provider-qualified model identifier before submitting audio. For local media, repeatable shell workflows, subtitle generation, or quick model comparisons, use the official Speechall CLI. It provides the same provider abstraction as the REST API without requiring one-off integration code.

Speechall does not currently offer a public MCP server or third-party outbound webhook product. The billing webhook endpoint is an internal Stripe integration and is not an external integration surface. We document this explicitly so agents can choose the REST API, SDK, or CLI instead of relying on an unavailable integration.

Read Speechall API Docs