41 params recognised on the Deepgram session (/v1/listen with a DG credential). Rendered live from app/api/v1/_dg_params.py.
| Param | Behaviour | Note |
|---|---|---|
encoding | SUPPORTED | Parakeet expects PCM-16 (linear16); transcode mulaw/alaw/opus. |
sample_rate | SUPPORTED | Parakeet trained at 16 kHz; resample any declared rate. |
endpointing | SUPPORTED | Silero/WebRTC VAD; emit speech_final after silence>endpointing ms. |
language | SUPPORTED | Parakeet-TDT-0.6B-v3 supports 25 languages; pass as model hint. |
numerals | SUPPORTED | Parakeet TDT head includes ITN; enable via model config. |
interim_results | SUPPORTED | Stream partial Results frames; if false buffer to final only. |
utterance_end_ms | SUPPORTED | Silence (ms) after last word before UtteranceEnd fires; drives SDK end-of-speech timing. None falls back to VAD default. |
vad_events | SUPPORTED | Silero/WebRTC VAD; emit SpeechStarted + UtteranceEnd frames. |
words | SUPPORTED | Parakeet provides word-level timestamps natively. |
| Param | Behaviour | Note |
|---|---|---|
channels | PARTIAL | Accept up to 2; mix to mono internally. |
model | PARTIAL | Accept any value, route to Parakeet, echo in metadata.model_info.name. |
punctuate | PARTIAL | Parakeet basic punctuation; post-processor for accuracy. |
diarize | PARTIAL | Baseline speaker:0. When DDX_STT_DIARIZE_ENABLED=1, real Sortformer speaker labels on words[] (en supported; de/fr/es EXPERIMENTAL). |
smart_format | PARTIAL | Baseline: punctuate + numerals. When DDX_STT_SMART_FORMAT_ENABLED=1, engages WFST ITN on the FINAL transcript (en production; de/fr/es EXPERIMENTAL). |
replace | PARTIAL | Repeatable 'search:replace'; simple string-replace post-processor. |
keywords | PARTIAL | Repeatable 'kw[:intensifier]'; pass to NeMo hot-word biasing if avail. |
keyterm | PARTIAL | Nova-3 only; max 500 tokens; no-op initially. |
utterances | PARTIAL | Per-utterance segmentation via VAD + utterance_end_ms silence. |
utt_split | PARTIAL | Silence threshold seconds; map to VAD min_silence_ms. |
turn_detection | PARTIAL | Dudoxx ext (shard 06). Silero endpointing is default. When DDX_STT_TURN_DETECTOR_ENABLED=1, a semantic EOU model REFINES each Silero speech_end (true turn-end vs mid-utterance pause); off = Silero only. |
filler_words | PARTIAL | Parakeet drops fillers by default; toggling needs model-config change. |
| Param | Behaviour | Note |
|---|---|---|
version | NOOP | Legacy Deepgram field; accept silently, ignore. |
tier | NOOP | Legacy Deepgram field; accept silently, ignore. |
profanity_filter | NOOP | Accept; return unfiltered initially. Regex pass deferred. |
redact | NOOP | Accept; return unredacted. Roadmap. |
no_delay | NOOP | DG smart_format no-delay flag; our streaming path emits without an endpointing buffer delay already, so honour-but-noop (echoed). |
tag | NOOP | Repeatable opaque analytics tag; accept silently, log only. |
extra | NOOP | Opaque echo-back string; surface in opening Metadata transaction_key. |
mip_opt_out | NOOP | Model-improvement opt-out; honour silently (no audio retention anyway). |
callback | NOOP | Async callback URL; not applicable to streaming WS. |
callback_method | NOOP | POST/GET/PUT/DELETE for async callback; ignored in streaming. |
paragraphs | NOOP | Accept; omit paragraph structure from response. |
summarize | NOOP | Invariant 8: NEVER call server-side LLM; return null/empty. |
detect_language | NOOP | Invariant 8: NEVER call server-side LLM; return null languages. |
detect_topics | NOOP | Invariant 8: NEVER call server-side LLM; return empty topics. |
detect_entities | NOOP | Invariant 8: NEVER call server-side LLM; return entities:[]. |
dictation | NOOP | Spoken commands as regular words; no command interpreter. |
search | NOOP | Repeatable; omit search_results from response. |
alternatives | NOOP | Always return 1 alternative; SDK handles missing N-best gracefully. |
authorization | NOOP | SDK per-request key override; the WS handler reads Authorization header. |
| Param | Behaviour | Note |
|---|---|---|
multichannel | ERROR | Reject if true with channels>1: close 1008 'multichannel not supported'. |
These params are honoured ONLY when their server env flag is on; otherwise they keep today's baseline behaviour (speaker:0 / verbatim text / Silero-only endpointing). EXPERIMENTAL languages run but correctness is not guaranteed.
| Param | Production langs | EXPERIMENTAL langs | Notes |
|---|---|---|---|
diarize | en | de, es, fr | Sortformer speaker labels on words[].speaker (additive extension field). Gated by DDX_STT_DIARIZE_ENABLED. |
smart_format | en | de, es, fr | WFST inverse text normalization on the FINAL transcript. Gated by DDX_STT_SMART_FORMAT_ENABLED. |
turn_detection | de, en, es, fr, it, nl, pt | — | Semantic end-of-utterance refinement over Silero (fail-open). Gated by DDX_STT_TURN_DETECTOR_ENABLED. |