Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
MiFID II and FCA call recording: compliance for voice transcription in finance
TL;DR: Financial firms operating under MiFID II and FCA jurisdictions must maintain searchable, high-accuracy records of all client-related voice communications, including remote and mobile calls under FCA Market Watch 66. Engineering and product teams building for these obligations typically implement dedicated cloud infrastructure with defined data residency, controls that prevent customer audio from being used to retrain models on Growth and Enterprise plans, and transcription accurate enough that the resulting records hold up under regulatory review. Transcription and speaker attribution errors are not product quality issues in this context. They are audit trail failures, and regulators treat them as such.
Why speech-to-text accuracy matters upstream of your LLM
TL;DR: Downstream LLM performance is ceiling-bounded by upstream transcription accuracy. A transcript with a meaningful error rate doesn't produce proportionally degraded summaries or CRM entries. It produces outputs where hallucinated names, inverted logic, and misattributed speaker turns compound silently into every downstream system that reads them. Prompt engineering cannot recover information the STT layer never captured. Gravite cut call quality review time by 93%, from 15 minutes to 1 minute per call, once transcript accuracy was high enough to trust the output without manual verification.
TL;DR: Telephony audio is constrained to 8kHz narrowband frequencies, stripping away the high-frequency spectral energy that generic 16kHz STT models require. Standard upsampling cannot recover phonemes that were never captured at the source, leading to transcription errors that compound silently into downstream NLU failures. Solaria-3 ranks #1 on Switchboard, the most challenging conversational telephony dataset, ahead of AssemblyAI, ElevenLabs, Deepgram, Mistral, and Speechmatics, ensuring your downstream LLM pipelines receive clean, structured data from real-world noisy call audio.
How to integrate live transcription API with Twilio to transcribe calls in real time
Published on Sep 28, 2023
Twilio, used by hundreds of thousands of businesses and more than ten million developers worldwide, can now integrate with our live transcription API. The integration makes it easier for users to natively transcribe any phone call in real time while using Twilio. With transcribed text at your disposal, you'll then be able to analyze, archive, and act upon voice data more effectively.
Below, you’ll find a step-by-step guide on setting up the Twilio integration with Gladia API in JavaScript for free.
What can you do with Twilio integration?
Any developer can use this integration to transcribe phone calls in real-time.
How to implement Twilio + Gladia real-time transcription integration
Step 1: Set up your Gladia account
If you haven't already, sign up for our Speech-to-Text API at app.gladia.io and obtain your API key.
Step 2: Create and parametrize your Twilio account
Get a phone number, following the first step of the main page to connect to your Twilio account.
On the left panel Develop > United States (US1) > Phone Numbers > Manage > Active numbers.
Click on the phone number you just created.
In 'Configure' panel, 'Voice Configuration' section, 'A call comes in' field, choose 'Webhook' with URL = 'http://[your-id-address]:[your-app-port-number]' and HTTP = 'HTTP POST'
Step 3: Configure your server and install dependencies
In .env file, add GLADIA_API_KEY var with your API key obtained from Gladia’s website and PORT var, the port you used to configure your phone number in above section (default is 8080)
Feel free to check out the video version of the tutorial for a step-by-step walkthrough with one of our software engineers, Antoine.
We hope you enjoyed this how-to tutorial! Given how much audio data still goes to wasted, we’re always curious to explore the many ways in which transcription tech can be used to remedy that. Let us know if you end up using our API with Twilio, Discord, or other, we’d love to hear from you.
About Gladia
At Gladia, we built an optimized version of Whisper in the form of an API, adapted to real-life professional use cases and distinguished by exceptional accuracy, speed, extended multilingual capabilities and state-of-the-art features, including speaker diarization and word-level timestamps.
Contact us
Your request has been registered
A problem occurred while submitting the form.
Read more
Speech-To-Text
MiFID II and FCA call recording: compliance for voice transcription in finance
Speech-To-Text
Why speech-to-text accuracy matters upstream of your LLM
