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.
TL;DR: In a natural voice agent conversation, anything over 500ms end-to-end feels stilted. Transcription latency is the first line item in that budget, and it sets the ceiling for everything downstream. This guide walks through wiring Solaria-1 into a Pipecat pipeline, tuning VAD thresholds, and handling failure modes, so the STT layer is a decision you can revisit without a rewrite. Because each component is independently swappable, choosing your STT provider is an architectural constraint you control, not one the framework imposes.
TL;DR: Voice agent latency comes from every layer, but the LLM accounts for the largest share of your total budget. Self-hosting open-source STT models burns GPU budget on cold-start delays and accuracy that degrades on accented speech. Integrating our Solaria-1 streaming API with LiveKit gives you partial transcripts in under 103ms and final transcripts at approximately 300ms, with true code-switching across 100+ languages. This guide delivers production-ready Python and Node.js code to connect LiveKit's audio egress to Gladia, configure silence detection, and drive natural turn-taking using live partials.
TL;DR: Recall.ai handles the platform-level complexity of joining Zoom, Meet, and Teams calls while we handle transcription, diarization, and enrichment. This guide walks through the full integration: spawning a bot, routing recorded audio to our async API, enabling pyannoteAI Precision-2 diarization, and mapping speaker labels to participant names using timestamp overlap. Choose Solaria-3 for post-meeting accuracy on English and European business audio, Solaria-1 for real-time captions or broad language coverage. On Growth and Enterprise plans, your audio is never used to train our models.
Integrating Gladia audio transcription API with Make for workflow automation
Published on Dec 20, 2023
Embark on a journey to optimize your workflow by seamlessly integrating Gladia through Eden AI with Make. This comprehensive guide will take you through the step-by-step process, empowering you to harness the full potential of automation in your tasks.
What is Make?
Make is a no-code automation platform that helps companies time and resources by connecting all of their favorite apps on Make with just a few clicks. Contrary to traditional integration and automation platforms, known for being siloed and non-intuitive, Make makes workflow automation accessible, versatile, and easy to use.
Benefits of using Gladia with Make
Gladia is a speech-to-text (STT) and audio intelligence API enabling AI audio and video transcription. It supports 99 languages, has enhanced language detection with code-switching, and unlocks several valuable features like speaker diarization, live transcription, and word-level timestamps. Our latest model, Whisper-Zero, eliminates virtually all hallucinations from transcripts.
Integrating an audio transcription API into a workflow automation platform like Make can bring several benefits, such as:
Audio data integration: First and foremost, STT APIs help companies capture and utilize audio data to inform business intelligence across workflows.
Error reduction: Cutting-edge STT technology minimizes the risk of typographical errors that commonly occur during manual typing, ensuring accuracy and reliability of data across workflows.
Multimodal interaction: Integrating speech capabilities into a workflow automation platform allows users to interact through multiple channels (voice and text), catering to diverse user preferences.
Data insights and analysis: Transcribed text from speech inputs can be analyzed for patterns, sentiments, or keywords, providing valuable insights for improving services or optimizing workflows.
This tutorial will explain how to leverage Gladia’s transcription engine with Make via EdenAI, a one-stop-shop platform for the best developer APIs.
Step 1: Navigate Make marketplace
Begin your integration journey by visiting the Make.com marketplace. Search for the Eden AI app integration to explore its many capabilities.
Preview of EdenAI's app
Within the Eden AI integration, you’ll find several AI feature actions that will serve as pillars for introducing Eden AI into your automated workflows.
Step 2: Scenario setup on Make
Access your Make account and initiate the creation of a new scenario. Select a module that aligns with your workflow, such as Gmail or Google Drive, to kickstart the automation process.
Integrate a new module into your scenario and locate Eden AI within the available options. This step is pivotal in establishing a seamless connection between Make and Eden AI.
Upon selecting Eden AI, narrow down the specific event that will trigger your scenario. In this case, search for "Transcription".
Step 3: Connecting your Eden AI account
If you haven't done so already, create an account on Eden AI using the provided referral link. This account will be the gateway to unlocking the powerful capabilities of Eden AI and Gladia.
Retrieve your API key from the homepage of Eden AI. You just need to paste it into the designated field.
Step 4: Configuring the Eden AI module
Input the file you wish to analyze seamlessly. For example, if your data originates from Gmail attachments, seamlessly integrate it into the Eden AI workflow for thorough analysis.
Choose "Gladia" as provider and configure the action to specify where you want the analyzed data to be stored. Popular choices include platforms like Google Sheets. Note that we support automatic language detection, code-switching, and can transcribe language correctly whatever the accent.
Step 5: Saving and activating your scenario
With the configuration complete, your scenario is ready for action. Activate it to witness the transformative power of Gladia in automating your tasks.
Explore the Gladia functionality within Make to efficiently manage and utilize the analyzed data as per your workflow requirements.
Streamline your integration process by searching for "Eden AI" templates tailored to your specific needs. This bonus tip ensures a quicker implementation of Eden AI into your scenarios.
Conclusion
Integrating a reliable speech-to-text API like Gladia into Make.com could significantly enrich its functionality, making interactions more efficient, accurate, and accessible for users across various industries and purposes. We hope this quick guide was helpful to get you started.
To learn more about our partnership with EdenAI, feel free to check their blog.
Contact us
Your request has been registered
A problem occurred while submitting the form.
Read more
Speech-To-Text
Add speech-to-text to a Pipecat voice agent
Speech-To-Text
Add speech-to-text to a LiveKit voice agent
Speech-To-Text
Add speech-to-text to a Recall.ai meeting bot
From audio to knowledge
Subscribe to receive latest news, product updates and curated AI content.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
