🎙️ Speech-to-Text API — Test Client

API base URL
User ID (scopes everything)
Processing options (applied to new uploads)
Template
Summary length
Summary language
Translate transcript to
Exact # speakers
Max speakers
Custom prompt (overrides template)
Audio files
🎵
Drop audio here, or click to browse
MP3 · WAV · M4A · FLAC · OGG · WebM
My Recordings (Home screen — scoped to User ID)
Enter a User ID above and click Load.
WebSocket URL
Translate live to
🎤 Live Microphone
Speak into your mic — partial transcripts appear live. On Stop you get the speaker-attributed final transcript and an auto-created summary task.
Audio Files
🎵
Drop files here, or click to browse
Streamed in real time; a detailed summary task is auto-created on stop
Add audio files above to get started