Vapi adds Soniox confidence filter and latency limits in simulations
The Vapi platform now allows discarding low-confidence Soniox transcriptions and controlling latency in voice agent simulations.
Read articleVoiceIP editorial
Voice technology through a business lens: what changed, how it works and what to check before implementation.
Our coverage
The VoiceIP journal covers voice AI agents, speech recognition and synthesis, telephony and communications within business processes. VoiceIP is an Intecracy Group project. Current journal articles are authored by VoiceIP editorial.
Sources and updates
We base news reporting on official announcements, documentation and provider changelogs. Each article links to its primary sources. We distinguish stated product capabilities from practical analysis, and application scenarios from delivered customer projects.
The original publication date stays unchanged. Substantial revisions receive a separate update date. Historical articles remain available in the archive at their original URLs.
Authors and commentators
Comments add a business or technical perspective to the news. Each links to a profile describing its subject area and related articles. Author commentary does not imply authorship of the entire article.
Fictional editorial identities are labelled on their profiles. Editorial comments prepared for profiles are the editorial team’s analysis within those subject areas, not verbatim statements, interviews or evidence of personal approval.
Latest from the journal
Deepgram adds pause and pronunciation controls to Flux TTS
Deepgram introduced pause and pronunciation controls directly in the text for Flux TTS. The update allows inserting silence and specifying IPA transcriptions.
Read article
ElevenLabs releases Eleven v4 and v4 Turbo speech synthesis models
The new models support emotion control via tags and over 90 languages. According to ElevenLabs, the median time to first speech is around 150ms.
Read article