Speech 2.5 HD Preview Voice Clone is a MiniMax model exposed on the Huzz API with a single Huzz key and one consistent, OpenAI-compatible interface. Capabilities: File upload, Voice cloning, Voice conversion. Long-running jobs run asynchronously with polling. Call it at https://api.huzz.ai using Authorization: Bearer $HUZZ_API_KEY — no per-provider accounts or SDKs required.
FamilyCapabilitiesStreamingAsyncPricing
MiniMaxFile upload, Voice cloning, Voice conversionNoYesUsage-based

​
Endpoints

MethodPathCapability
POST/api/v3/minimax/speech-2.5-hd-preview-voice-clone/file-uploadFile upload
POST/api/v3/minimax/speech-2.5-hd-preview-voice-clone/voice-cloneVoice cloning
POST/api/v3/minimax/speech-2.5-hd-preview-voice-clone/voice-to-voiceVoice conversion

​
Code samples

Authenticate with Authorization: Bearer $HUZZ_API_KEY — get a key at huzz.ai/register. 
curl https://api.huzz.ai/v1/chat/completions \
  -H "Authorization: Bearer $HUZZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "speech-2.5-hd-preview-voice-clone",
    "messages": [{"role": "user", "content": "Hello from Huzz!"}]
  }'
Long-running jobs return a prediction id. See Async predictions for the full submit-and-poll lifecycle.