feat: add u3-rt-pro model support to assemblyai_asr_python#2081
Open
dan-ince-aai wants to merge 1 commit intoTEN-framework:mainfrom
Open
feat: add u3-rt-pro model support to assemblyai_asr_python#2081dan-ince-aai wants to merge 1 commit intoTEN-framework:mainfrom
dan-ince-aai wants to merge 1 commit intoTEN-framework:mainfrom
Conversation
- Add `speech_model` config field (universal-streaming-english, universal-streaming-multilingual, u3-rt-pro); defaults to u3-rt-pro - Add new fields: `min_turn_silence`, `language_detection`, `prompt`, `vad_threshold`, `speaker_labels`, `max_speakers` - All optional params omit from WS URL when unset, letting API defaults apply - language_detection auto-enabled for u3-rt-pro and multilingual models - prompt param guarded to u3-rt-pro only (logs warning otherwise) - Deprecate `min_end_of_turn_silence_when_confident` in favour of `min_turn_silence`; old param still accepted as fallback - Fix WebSocket message type casing: ForceEndpoint, UpdateConfiguration - Add User-Agent header for TEN-Framework integration tracking - Update manifest.json and property.json with new fields Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
speech_modelconfiguration field supportinguniversal-streaming-english,universal-streaming-multilingual, andu3-rt-pro; defaults tou3-rt-prou3-rt-pro:language_detection,prompt,vad_threshold,speaker_labels,max_speakersmin_turn_silenceto replace the deprecatedmin_end_of_turn_silence_when_confident(old param still accepted as fallback)language_detectionis automatically enabled foru3-rt-proand multilingual modelspromptparam is guarded tou3-rt-proonly (logs a warning if set on other models)forceEndpoint→ForceEndpoint,updateConfiguration→UpdateConfigurationUser-Agent: AssemblyAI/1.0 (integration=TEN-Framework)header for integration trackingmanifest.jsonandproperty.jsonwith new fieldsTest plan
speech_model: u3-rt-proand verify WebSocket URL includesspeech_model=u3-rt-proandlanguage_detection=truespeech_model: universal-streaming-englishand verifylanguage_detectionis not sentpromptwith a non-u3-rt-pro model and confirm it is ignored with a warning logmin_turn_silenceand confirm it appears in the URL; set neither silence param and confirm neither appearsForceEndpointandUpdateConfigurationmessages are accepted by the API without errortest_error_checkintegration test still passes🤖 Generated with Claude Code