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.
Transcribe phone calls and push them to HubSpot with Gladia and Zapier
TL;DR: Every wrong name or missed entity in a call transcript silently corrupts your CRM data downstream, and self-hosted pipelines compound this with GPU maintenance overhead and poor accuracy on accented speech. This guide shows you how to route call recordings from Twilio or Aircall through Zapier to our async API, run LLM extraction on the diarized transcript, and push structured deal properties and engagement logs to HubSpot without maintaining custom infrastructure. Multiple customers have the Gladia API layer running in under 24 hours. The remaining pipeline configuration time depends on your Zapier, LLM, and HubSpot setup complexity.
Cutting transcription cost per audio hour for meeting assistants
TL;DR: Transcription cost and accuracy are critical drivers of unit economics for meeting assistant builders. Headline API rates are deceptive because hidden fees for diarization, translation, and billing increments routinely double the effective cost per hour. Self-hosting open-source models introduces GPU underutilization and DevOps overhead that can exceed managed API costs by approximately 3x at early-stage volume. Teams that switch to all-inclusive pricing (diarization, translation, and sentiment bundled at as low as $0.20/hr on our Growth plan) recover meaningful margin without waiting for enterprise-tier volume to justify the conversation.
Scaling real-time STT for high-concurrency voice agents
TL;DR: Scaling real-time voice agents to hundreds of concurrent calls requires moving from stateless CPU-based autoscaling to stateful WebSocket connection management. The failure mode is predictable: architectures that handle test calls at low concurrency struggle when traffic spikes, producing latency spikes and dropped audio. The fix involves scaling on active connection counts, implementing ping/pong heartbeat monitoring to reclaim hanging sessions, and enforcing hard connection limits to protect downstream LLM and TTS layers. Additional capacity comes online without pre-provisioning, so the STT layer is not a fixed ceiling as session counts grow.
How Gladia's multilingual audio-to-text API supercharges Carv's AI for recruiters
Published on Apr 3, 2024
In today's professional landscape, the average workday of a recruiter is characterized by a perpetual cycle of administrative tasks, alternated by intake calls with hiring managers and interviews with candidates. And while recruiters enjoy connecting with hiring managers and candidates, there’s an almost universal disdain for the administrative side of the job.
Taking interview notes, writing job descriptions, drafting candidate profiles — these are just few of the many admin tasks that require precious time and attention, but leave recruiters with little opportunity to prioritize more candidate centric initiatives.
And that’s where Carv comes in. The company aims to revolutionize recruiting by integrating AI into the interview process, saving recruiters hours that can now be spent on more impactful initiatives.
A key component in this workflow is capturing relevant data and insights from recruitment calls, for which Carv relies on multilingual AI transcription provided by Gladia.
About Carv
Carv is AI for recruiters, purpose-built to take over admin tasks related to intake calls & interviews. Their mission is to unburden recruiters by eliminating admin so they can prioritize the human aspect of hiring. Carv listens in on job intake calls and interviews and uses the context of those meetings to fully automate admin tasks, reducing time spent on tedious tasks from hours to minutes.
Founded in Amsterdam in 2022, the company of 25 employees targets recruiting teams and staffing agencies around the globe.
Challenge
As the recruitment landscape evolves, the need for efficient and streamlined hiring processes grows increasingly important. After all, good talent is hard to find, and providing recruiters with the tools necessary to build meaningful connections with the right candidates is paramount in getting the right people in.
Carv’s founders recognized the challenges faced by recruiters – the significant amount of time spent on repetitive administrative tasks rather than focusing on the human being in front of them. They asked themselves the question: How can we unburden the recruiter so that they can focus on the interactions that truly matter?
Leveraging the momentum created by the emergence of generative AI, the company enlisted the help of state-of-the-art Large Language Models (LLMs) and prompt engineering to address this very issue.
The result is a versatile AI platform that accompanies recruiters in every intake conversation and candidate interview.
Transcription, which serves to convert these meetings into input for LLMs, plays a key role in Carv's mission to optimize productivity for hiring teams. After all, without the right context and accurate data for the LLM, generating top-quality insights for recruiters to work with efficiently is next to impossible.
Choosing the right provider to establish this foundation was therefore paramount for Carv to ensure no nuance is lost in the process.
Objectives
Before switching to Gladia, Carv used another API provider that didn’t provide the range of language support necessary to serve Carv’s international client base. With a user base originating from over 90 countries, flawless multilingual support was critical.
Gladia met their needs based on the following criteria:
High-quality transcription at a scalable cost;
Language support for transcription and audio intelligence in 99+ languages, with enhanced sensitivity to accents and top accuracy in less widely-spoken languages like Dutch, Albanian and Kazakh;
Code-switching, i.e., the ability to detect and transcribe a meeting where multiple languages are used interchangeably.
Solution
Enter Gladia! Using our speech-to-text and audio intelligence API, the Carv team was able to implement and improve must-have features like:
AI-generated job descriptions based on intake calls with the hiring manager;
AI-generated candidate profiles, based on interviews with candidates;
Meeting notes, so recruiters can focus on the interview;
Free format prompting, for highly specific use cases.
Preview of Carv's core features powered by Gladia
Impact
By working with the Gladia team to iterate and scale up, they saw a noticeable impact on their speed of shipping and iteration, with the underlying transcription engine enabling more and more valuable capabilities for Carv's AI for Recruiters.
The team at Carv is already looking forward to implementing more features at the intersection of Gladia APIs and Carv’s proprietary know-how. According to Carv’s VP of Product & Engineering, Valentijn van Gastel, Carv’s future vision involves addressing specific use cases and problems for customers in different types of recruitment, where Gladia's expanding audio intelligence offering could be of service.
We're thrilled to be part of this amazing journey with them, and thank Carv for putting their trust in us! As we move forward, we're excited to team up with more clients, tackle new challenges, and make speech AI more accessible to virtual meeting companies worldwide.
About Gladia
Gladia provides a speech-to-text and audio intelligence API for building virtual meeting and note-taking apps, call center platforms, and media products, providing transcription, translation, and insights powered by best-in-class ASR, LLMs and GenAI models.
Having read this case study, do you feel like Gladia could be the right fit for your business too?
