Loading models…
STT · Speech to Text
Upload audio and send a multipart request to /v1/audio/transcriptions.
Your transcription will appear here.
TTS · Text to Speech
Enter text, call /v1/audio/speech and play the returned WAV audio.
Generated audio will play here.
Available ModelsBrowse STT / TTS models, supported languages and model sizes
Live data from /v1/models. Language names come from model metadata; “Auto” means the model or router detects the language.
STT · Speech Recognition Models
Loading models…
TTS · Speech Synthesis Models
Loading models…
Application Integration Examples
Model discovery and inference use standard HTTP. These examples use the currently selected model IDs.