API Authentication
Authentication is not enabled on this server. All API endpoints are publicly accessible.
Authentication is not enabled on this server. All API endpoints are publicly accessible.
Transcribe your microphone live with Parakeet, or record/upload audio for any recognition model.
Match a known transcript to the audio above. Supports audio up to 5 minutes in 11 languages and returns word timings.
Enter text and receive a voice recording you can play.
[laughing nervously]. Tip: (paren) sound cues like (laugh) exist but can produce long non-speech — use sparingly. First run loads the model (~20s); generation is slower than realtime.Record a sample of your voice to create a voice clone that can be used for text-to-speech with any model.
No transcript needed - just provide a voice sample.
No voice clones yet. Create one above!
Import a previously exported voice clone (.zip file).
Requires a transcript of the voice sample (auto-detected).
No voice clones yet. Create one above!
Import a previously exported Qwen3 voice clone (.zip file).
Use 1-30 seconds of clean speech (5-10 seconds recommended). No transcript is needed.
No reference voices yet. Create one above!
Zero-shot cloning from 1-30 seconds of clean speech (5-15s recommended) plus its transcript.
No voice clones yet. Create one above!