Realtime
Recorded
Concepts
Guides
API Reference
Changelog
API-breaking changes, new fields, deprecations.
2026-11-09
Realtime refinement is available with Lite and Pro profiles
session.update.refinementopts a session into per-utterance AI refinement.trueselects the defaultliteprofile;"lite"/"pro"select a profile explicitly;falsedisables it. It is off by default and fixed before audio; later changes returnsession_features_locked.- Lite uses a one-sentence prompt, two segments of context, and tight character/completion budgets. It is included in the base transcription price.
- Pro uses the full prompt, ten segments of context, and a rolling guide. It is billed at +$0.012/min on top of the realtime base rate.
session.created.features.asr_correctionreports whether refinement is available on the gateway;features.refinementreports the enabled profile id (false,"lite", or"pro").- New
gateway.correction.configuredlifecycle event records the profile and prompt version. - Rate card published.
GET /v1/pricingnow returnsrate_card_status: "published"; the pricing preview banner is removed. - See Pricing for the current rates.
2026-11-08
Recorded translation is available
target_languages(array, max 8) andtranslate_to(single-language shorthand) now work onPOST /v1/audio/transcriptions/jobs. The target set is frozen at job creation.- New
result.translations[]— one track per target language, with per-segmentid, timestamps, translatedtext, andsource_text. - New
result.metadata.translation— model,failed_batches, and token usage (calls,prompt_tokens,completion_tokens,total_tokens). - New
result.metadata.llm_usage— whole-job token usage across refinement and translation, including aby_stagebreakdown. Realtime usage events also recordllm_usageper flush. - Pricing. Recorded translation is billed per target language × processed audio duration. See Pricing.
Documentation naming and contract clarification
- Lanson Live API is the developer-facing speech capability; Lanson Live App is the end-user product. LansonAI remains the company and platform brand.
- Lanson Live is the speech model brand, with model name
lanson-live-1. Integrations do not need to select a model; the optional HTTP compatibility parameter can be omitted. Existing client request values and API paths are unchanged. - Trinity Engine, StableStream™, and LiveFinal™ now have distinct engine, output-technology, and correction/finalization roles. New LiveFinal™ documentation maps the mechanism to current public events.
- The public Realtime endpoint delivers one completed result per successfully processed utterance. Optional refinement happens before delivery; no partial/revision or session-wide final event is implied by the technology names. Manual flush is an accepted compatibility message, not an implemented finalization command on this endpoint.
- These are documentation corrections, not a newly released model-routing or event protocol.
2026-11-07
Realtime translation is available
session.update.target_languages(and thetranslate_toshorthand) enables realtime translation. Up to 8 BCP-47 targets per session.- Session-fixed features. The first accepted target set is frozen before audio; later changes return
session_features_locked. Start a new session to change targets. - New
session.updatedevent confirms the appliedlanguage,target_languages, andfeatures. - New
live.translation.completedevent carries one translation per utterance and target language. It arrives independently of the source transcript. - Pricing. Realtime translation is billed per target language × processed audio duration. Refinement is now also separately billed when enabled. See Pricing.
- Recorded translation was added on 2026-11-08 (see above).
2026-11-06
Documentation corrections
- Realtime
languageis optional. All examples now show the recommended explicit code, while documenting that omitting it (orauto) enables auto-detection. Passing a known language is recommended for accuracy. - Mid-session language switching. A
session.updatewith"auto"resets detection and re-detects on subsequent speech; a concrete code always wins. This supports sessions that start in one language and switch after another appears. - Two auto modes documented. Clients can detect first with
POST /v1/audio/language-detectionand send an explicit code, or omit the language and let the session use its internal detection strategy. - Additive event fields.
conversation.item.input_audio_transcription.completednow exposeslanguage_source,language_provisional, and optionallanguage_detection_error(also mirrored insidetranscript). Existing fields are unchanged. - Language detection is documented. New
POST /v1/audio/language-detectionreference for clients that do not know the language up front. - Binary frames are not supported today. The realtime examples and the server-side guide now use base64 JSON
input_audio_buffer.appendframes. - Segment
languageis required. Missing orautoreturns400 invalid_language. - Batch
reviewdefaults to on. Documentation now matches the OpenAPI schema: omitted = on,review: falseopts out. - Server event examples updated for the current
completedpayload (raw_text,stt_endpoint,worker_id,transcript) andsession.created.features. - Corrected confidence/timestamp examples (
confidence: 0when unavailable,timing: "estimated"on the batch path) and clarified that SRT/VTT generation is client-side.
2026-08-22
API paths
- Batch jobs — preferred enqueue:
POST /v1/audio/transcriptions/jobs(JSONaudio_url, 202). - Poll — preferred:
GET /v1/audio/transcriptions/jobs/{workflow_id}(opaque id:local+ 32 hex on the production endpoint,cf_+ 64 hex on the Cloudflare Worker deployment). - Segment —
POST /v1/audio/transcriptionsis now documented as multipart-only synchronous client-VAD transcription (200). - Deprecation —
POST /v1/audio/transcriptionswith JSON still works but returnsDeprecation: trueandLink: </v1/audio/transcriptions/jobs>.
Documentation
- New Segment Transcription API reference.
- Batch Jobs split from the old combined transcription page.
- Client-VAD segments guide.