Skip to main content
STT models accept additional configuration via the json_config parameter. In the Python SDK, this is a dict mapping option name to value (float or string). When using the REST endpoint, pass it as a URL-encoded JSON string in the json_config query parameter. These options apply to both the WebSocket and REST transports. For TTS settings, see Voice Settings.

​
Quick reference

OptionTypeAllowed valuesEffect
tempfloat0.0–1.0Sampling temperature for text generation. 0.0 is greedy; higher values produce more diverse output and can help when no text is being recognised.
languagestring"en", "fr", "de", "es", "pt"Expected language of the audio. Grounds the model to a single language for better transcription quality. For mixed audio, set the main language. Any other value raises a server error.
padding_bonusfloat-4.0–4.0Biases the model toward emitting text sooner (negative) or later (positive). Out-of-range values raise a server error.
delay_in_framesint7, 8, 10, 12, 14, 16, 20, 24, 32, 36, 48Adaptive delay control. Each frame is 80 ms of context before text is emitted. Higher values improve quality at the cost of latency; lower values are more reactive. Other values raise a server error. The legacy alias delay_in_tokens is also accepted.
Default values may evolve with new model releases. Pin the options explicitly if you depend on a specific behaviour. The server validates known keys with the constraints above; unknown keys are silently ignored, so double-check spelling against the table.

​
Passing json_config

The same json_config payload is sent regardless of which SDK API you use; only the call shape differs: 
config = {"language": "en", "temp": 0.3, "delay_in_frames": 16}

# Pull-based: setup is a dict containing json_config.
stream = await client.stt_stream(
    {"model_name": "default", "input_format": "pcm", "json_config": config},
    audio_generator(audio_data),
)

# Real-time: setup is keyword arguments; json_config stays nested.
async with client.stt_realtime(
    model_name="default",
    input_format="pcm",
    json_config=config,
) as stt:
    ...
When calling the REST endpoints directly, pass json_config as a URL-encoded JSON string in the query parameters, see the REST guide.

​
Semantic VAD and delay

delay_in_frames is most useful with the WebSocket STT stream. The server emits semantic VAD step messages every 80 ms; each step contains future horizons with inactivity_prob values. A common starting point for voice agents is to watch the longest horizon and flush when the inactivity probability stays above your threshold. 
if msg["type"] == "step":
    turn_done = msg["vad"][-1]["inactivity_prob"] > 0.5
    if turn_done:
        await stt.send_flush(flush_id=1)
Use lower delay_in_frames values for fast back-and-forth assistants, and higher values for transcription quality when a little more latency is acceptable.