EchoVox
Text-to-speech API for developers
Generate API keys, call REST endpoints, select voice IDs, and integrate EchoVox speech generation into products, agents, creator tools, and media pipelines.
Use the developer portal for quick cURL tests, key management, and production API onboarding.
Start with a reproducible request
Choose a voice ID and a short representative script before integrating a larger workflow. A known request gives a team a useful baseline for checking pronunciation, audio output, and later changes without guessing which input produced a particular result.
Manage API keys as account credentials
Keys are generated and managed after sign-in. Keep them out of browser code, public repositories, screenshots, and shared files. Revoke a key when the integration or the person responsible for it changes, then issue a replacement only where it is needed.
Record source and approval context
An API response is a production input, not proof that the audio is ready to publish. Store the source text, selected voice, output reference, and review status together so an editor or developer can trace a correction to the exact generation request.
Build permission checks into integrations
Any integration that uses a custom or cloned voice needs an authorization path before generation. Permission should be specific about the voice, allowed use, languages, channels, and time period; technical access must not become a way to impersonate someone.