The most powerful secure API for conversational Speech to Text
Word Error Rate: Less than 5%
Speed: Under 600 milliseconds latency
Pricing: Lowest on the market with commitment
Trusted by leading enterprises, integrators, and researchers
Express Language Model Adaptation
With our Language Model Factory (LMF), capture every specific vocabulary—train custom models in just 15 minutes and select the one that best fits your use case.
Pre-trained models for your sector & industry
Specific jargon & proper names
Acronyms
Industry-specific expressions
Securing and deleting sensitive data
Automatic redaction of sensitive information in real time based on your use cases: personal, financial, and healthcare data.
Transcription before redaction / Transcription after redaction
Speech-to-Text API for audio recordings
Simply upload your phone conversations to a secure FTP for transcription within minutes or use our connectors:
Available languages:
French, English, Spanish, German, Italian, +5 other European languages
Streaming API for Humans
Directly connect your audio streams via WebSocket to receive real-time, multi-speaker transcription, or use SIP Trunk / SIP REC.
Available languages:
French, English, Spanish and German
Streaming API for Bots
Stream API for IVR & Voicebot: Transcribe live interactions with our advanced solutions.
Powerful APIs to enable smooth interactions between users and bots. Whether you’re building an Interactive Voice Response (IVR) system over the phone or a voicebot connected to your dialogue system, our turnkey solution lets you transcribe even the most complex voice interactions.
Our protocols :
-
MRCP v2
-
WebSocket
Built-ins tailored for every interaction
Our turnkey built-ins manage speaking time, language model selection, and available grammar additions to personalize each voice interaction. Options include recognition of postal addresses, dates, numeric formats, and boolean responses (yes/no).
Available languages:
English, French, Spanish and German.
