Fetch a cloning sample with a signed grant
/v1/custom-voice-samples/{token}Serve the audio sample of a voice being cloned, to a provider that clones from a URL it fetches itself. The token is issued by AllModels for a single clone, expires after ten minutes, and is the only thing that authorizes the read — there is no other way to address a sample, and a voice ID cannot be turned into one. Every failure, expiry included, answers 404.
Path Parameters
Opaque grant issued for one clone, valid ten minutes.
1 <= lengthResponse Body
application/octet-stream
application/json
fetch("https://example.com/v1/custom-voice-samples/string", { method: "GET"})"string"{ "error": "not_found"}Search voices GET
Search voices available through AllModels. Filter by model, provider, language, category, or labels, and page through results with a cursor. No API key is required.
List your cloned voices GET
List your organization's cloned voices across all projects, newest first by default. Deleted voices are excluded. Each result contains a voice ID in `voice.id`, for example `AM:@narrator`. Use that ID as `voice` when generating speech.