Skip to main content
Gradium exposes Speech-to-Text over two transports. They share the same models; pick the transport that matches your audio source and latency needs.

​
Choosing a model

Two kinds of Speech-to-Text model are available, selected with model_name:
  • "default" — a standard transcription model. The transcription is produced in the language of the audio.
  • "stt-translate" — a translating transcription model. The transcription is generated in another language, which you choose with language (or target_language). See Transcription Settings.
Both kinds work identically over either transport.

​
WebSocket vs REST

If you’re transcribing pre-recorded audio and don’t need VAD, REST is the simpler path. Move to WebSocket when you need live audio, turn-taking, or in-stream flush.

​
What both transports share

  • Models: same model_name works on both.
  • Input formats: PCM (multiple sample rates), WAV, Opus, mu-law, A-law.
  • Tunable options: temp, language, padding_bonus, delay_in_frames, and a keywords dictionary for boosting names and jargon, all via json_config. See Transcription Settings.

​
What’s transport-specific

  • WebSocket-only: semantic VAD step messages every 80 ms, in-stream send_flush() for forced processing, adaptive delay controls (delay_in_frames), setup-message stream controls (send_setup_on_start, wait_for_ready_on_start), browser tokens. See WebSocket Lifecycle.
  • REST-only: send the full audio as the request body; receive NDJSON over a streaming response.

​
Next steps

Use the WebSocket API

Streaming audio in, transcripts and VAD signals out, with flush control.

Use the REST API

One-shot transcription of a complete audio file.

Turn-taking recipe

Use semantic VAD and adaptive delay to decide when an agent should answer.

Keyword boosting recipe

Recognize names, brands, and jargon by biasing STT toward a custom dictionary.

GitHub examples

Browse complete voice-agent demos built with Gradium STT and TTS.

Transcription settings

language, temp, padding_bonus, delay_in_frames.

Errors

Error contracts across REST, WebSocket, and streamed responses.