Release 0.9.0
  • Release Date: April 20, 2024
New Features
  • Add support for google v2 STT api
  • Add support for additional TTS vendors: PlayHT, RimeLabs, and Deepgram
  • Add support for streaming TTS (reduces latency) for Deepgram, ElevenLabs, Microsoft, PlayHT, RimeLabs, and Whisper
  • Add support for bidirectional audio in listen verb
  • Add new verb: dub to insert additional audio tracks into the conversation; see here for example usage.
  • Add boostAudioSignal to config verb allowing the volume of a conversation to be increased or lowered.
  • Add support for "filler" audio to the gather verb allowing brief audio to be played to a caller while the user application is processing a user utterance or dtmf collection, this can be useful in scenarios where an AI bot is expected to take a lengthy time to process a request
  • Add coach mode to conferencing, allowing for instance a manager to "whisper" to an agent on a 3-way conference with a customer
  • Add support for sending outbound OPTIONS pings to configured SIP trunks
  • If Deepgram endpointing is enabled, default utterance_end_ms to 1000 if none specified by the application (per Deepgram recommendation)
  • various improvements and enhancements to node-client-ws
Bug fixes
  • various fixes for Deepgram STT
  • 714 bargein "sticky" only works twice
  • 710 fix for actionHookDelay action
  • 671 handling of siprec invite failure
  • 666 transcribe on dial verb does not transcribe B leg by default
  • fix for precaching of TTS
  • check if sip gateway is in blacklist before sending outbound call
SQL changes
ALTER TABLE sip_gateways ADD COLUMN send_options_ping BOOLEAN NOT NULL DEFAULT 0
ALTER TABLE applications MODIFY COLUMN speech_synthesis_voice VARCHAR(256)
ALTER TABLE applications MODIFY COLUMN fallback_speech_synthesis_voice VARCHAR(256)
  • Available now on
  • devops scripts (packer, cloudformation, helm) available now for subscription customers

Questions? Contact us at