Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / ELEVENLABS
ElevenLabs low-latency streaming transcription via WebSocket, with partial/final utterances and voice-activity detection.
PRIMARY-SOURCE VERIFIED
ElevenLabs does not publish a token context window for this service. Input modalities: audio. Output: text. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
$0.39 per 60 audio minutes (realtime WebSocket hourly API rate).
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
Official WebSocket model_id is scribe_v2_realtime at wss://api.elevenlabs.io/v1/speech-to-text/realtime.
ElevenLabs official API rate is $0.39 per processed audio hour, expressed as per 60 minutes here (equivalent to $0.0065/minute). This is audio-time billing, not the cost of model-generated text.
Supports 90+ languages, manual or VAD commit, optional word-level timestamps and single-use browser tokens for client integrations.
Realtime and offline Scribe rates are different; compare using audio duration and streaming needs, never as token output rates.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for ElevenLabs Scribe v2 Realtime since 2026-10-12.
VERIFIED CHANGE HISTORY
Baseline verified: context not published · Not published max output · $0.39 per 60 audio minutes (realtime WebSocket hourly API rate)
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 77b0ad167e15…
COMPARE ELEVENLABS SCRIBE V2 REALTIME