# voice ai Technology that recognizes spoken audio as text and can synthesize text as spoken audio. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## PolyMO is a privacy-focused virtual pet built with an ESP32 and local AI DevFeed: [PolyMO is a privacy-focused virtual pet built with an ESP32 and local AI]() Original publisher: [Read original article]() Author: Ida Torres Published: 2026-09-17T00:30:05Z Content type: article Language: en Sources: [Yanko Design]() Topics: [ESP32](), [Hardware](), [Language models](), [Whisper](), [3D](), [voice ai](), [Android](), [Bluetooth]() Tags: [diy](), [gadgets](), [gadgets-technology-diy-virtual-virtual-pet](), [technology](), [virtual](), [virtual-pet]() ### AI overview PolyMO is a virtual pet designed to discourage excessive scrolling by becoming visibly ill when ignored. It combines an ESP32 device with an Android phone running local language, speech-recognition, and text-to-speech models, keeping conversations and pet behavior on the owner's hardware. ### Source excerpt Virtual Pet That Won't Let You Waste Your Life Scrolling Most of us know the feeling. You pick up your phone to check one notification, and forty-five minutes later you're three hundred posts deep into... ## How to Connect Your Twilio Agent to External APIs in Node.js DevFeed: [How to Connect Your Twilio Agent to External APIs in Node.js]() Original publisher: [Read original article]() Author: Dhruv Patel, Amanda Lange Published: 2026-09-14T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [AI Agent](), [Node.js](), [voice ai](), [REST API](), [OpenAI](), [Express]() Tags: [agent](), [ai](), [ai-agent](), [developer-insights](), [environment-variables](), [node-js](), [openai](), [rest-apis](), [visual-studio-code](), [voice]() ### AI overview This tutorial explains how to build a voice-enabled AI agent in Node.js with Twilio Conversation Relay and OpenAI. The agent uses LLM-driven tool calling to retrieve live data and take actions through an external REST API. ### Source excerpt Build a voice-enabled AI agent in Node.js with Twilio Conversation Relay and OpenAI to dynamically fetch live data from external REST APIs. ## How to Connect Your Twilio Agent to External APIs in Python DevFeed: [How to Connect Your Twilio Agent to External APIs in Python]() Original publisher: [Read original article]() Author: Amanda Lange, Dylan Frankcom Published: 2026-09-12T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [Python](), [API](), [FastAPI](), [AI Agent](), [voice ai](), [REST API](), [WebSocket](), [OpenAI]() Tags: [ai-agents](), [apis](), [developer-insights](), [fastapi](), [ngrok](), [openai](), [python](), [tutorial](), [visual-studio-code](), [voice-ai](), [websocket]() ### AI overview This tutorial explains how to connect a Twilio voice agent to an external REST API using Python and FastAPI. It demonstrates using LLM tool calling to fetch live data and take actions on a caller's behalf. ### Source excerpt Learn how to connect a Twilio voice agent to an external API using Python, so it can fetch real-time data and take action on a caller's behalf. ## How to Connect Your Twilio Agent to External APIs with PHP DevFeed: [How to Connect Your Twilio Agent to External APIs with PHP]() Original publisher: [Read original article]() Author: Amanda Lange, Matthew Setter Published: 2026-09-11T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [PHP](), [Tutorial](), [AI Agent](), [API](), [REST API](), [voice ai](), [.env](), [OpenAI](), [Composer](), [ide]() Tags: [agent](), [agents](), [apis](), [build](), [conversation-relay](), [developer-insights](), [external](), [how-to](), [openai](), [openswoole](), [php](), [rest-api](), [tutorial](), [voice]() ### AI overview This tutorial shows how to use PHP and OpenSwoole with Twilio Conversation Relay to build a voice agent that uses LLM tool calling to retrieve live data from an external REST API. It covers project setup, required packages, and storing an OpenAI API key in a .env file. ### Source excerpt In this tutorial, you will use PHP and OpenSwoole to build a voice agent using Twilio Conversation Relay. ## Build more natural voice experiences with GPT-Live-1 in the API DevFeed: [Build more natural voice experiences with GPT-Live-1 in the API]() Original publisher: [Read original article]() Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [voice ai](), [Large Language Model](), [Latency](), [asr]() Tags: [agents](), [api](), [audio](), [gpt](), [latency](), [llm](), [product](), [reasoning](), [release](), [text-to-speech](), [tool](), [voice]() ### AI overview GPT-Live-1 is launching in the API for full-duplex voice applications. The release emphasizes interruption handling, customizable conversational behavior, delegated reasoning and tool calls, long-session reliability, and telephony support. ### Source excerpt GPT-Live-1 brings natural, full-duplex voice conversations to the API, with stronger instruction following, custom voices, and telephony support. ## How to Build a Voice AI Agent with OpenAI's GPT-Live, Twilio Agent Connect, and Python DevFeed: [How to Build a Voice AI Agent with OpenAI's GPT-Live, Twilio Agent Connect, and Python]() Original publisher: [Read original article]() Author: Xinghao Huang Published: 2026-09-10T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [voice ai](), [AI Agent](), [Python](), [OpenAI](), [SDKs](), [API]() Tags: [ai](), [ai-agent](), [and-best-practices](), [api](), [backend](), [code](), [developer-insights](), [how-to](), [openai](), [python](), [sdk](), [tutorials](), [voice-ai]() ### AI overview A tutorial for building inbound and outbound phone voice AI agents with Python, Twilio Agent Connect, and OpenAI's GPT-Live. It covers tool calls, proactive greetings, per-call customization, and configuration for Twilio Media Streams. ### Source excerpt Build inbound and outbound voice AI assistants that can handle tool calls using Python, Twilio Agent Connect, and OpenAI's GPT-Live. ## Build Voice AI Experiences with Twilio and GPT-Live-1 in the OpenAI API DevFeed: [Build Voice AI Experiences with Twilio and GPT-Live-1 in the OpenAI API]() Original publisher: [Read original article]() Author: Lenore Files Published: 2026-09-10T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [voice ai](), [real-time](), [API](), [SDKs](), [OpenAI](), [Node.js](), [Python]() Tags: [ai](), [api](), [developer-insights](), [openai](), [real-time](), [tutorials](), [voice](), [voice-ai](), [websocket]() ### AI overview This tutorial article explains how to build real-time voice AI applications by connecting Twilio Agent Connect with OpenAI's GPT-Live-1 through the OpenAI API. It provides tutorials, sample applications, SDK support, and documentation for voice assistants and outbound voice agents using Node.js and Python. ### Source excerpt Build real-time voice AI Agents with Twilio and GPT-Live-1 in the OpenAI API with these tutorials, sample apps, and more. ## Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI DevFeed: [Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI]() Original publisher: [Read original article]() Author: Dmytro Hryshchenko, Abhijeet Dhumal Published: 2026-09-09T03:32:28Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Fine-tuning](), [voice ai](), [Training AI Models](), [Artificial Intelligence](), [distributed-training](), [GPU](), [lora](), [data](), [Open Source]() Tags: [ai](), [artificial-intelligence](), [distributed-training](), [fine-tuning](), [gpu](), [lora](), [open-source](), [speech](), [text-to-speech](), [training](), [voice](), [workflow]() ### AI overview This tutorial explains how to fine-tune the open source Orpheus-3B text-to-speech model for Turkish using Red Hat OpenShift AI and Kubeflow Trainer. It describes packaging distributed training in a TrainJob, scaling across nodes and GPUs, and using LoRA to keep memory usage below 16 GB. The reported result reduces speech errors by more than 90% compared with the base model. ### Source excerpt Can't Read, Won't Buy. That is the title CSA Research gave its survey of 8,709 consumers across 29 countries, and the numbers justify it: 76% prefer to buy in their own language, and 40% will never buy in another. The same rule governs what your product says out loud. The post Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI appeared first on Red Hat Developer. ## 5 ways to use Gemini text-to-speech (TTS) in your apps with Firebase AI Logic DevFeed: [5 ways to use Gemini text-to-speech (TTS) in your apps with Firebase AI Logic]() Original publisher: [Read original article]() Author: Ankita Saxena Published: 2026-09-09T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [voice ai](), [Artificial Intelligence](), [digital accessibility](), [Mobile](), [Web]() Tags: [accessibility](), [ai](), [ai-logic](), [firebase](), [firebase-ai-logic](), [gemini](), [mobile](), [speech](), [text-to-speech](), [web]() ### AI overview The article presents five use cases for Gemini text-to-speech through Firebase AI Logic, including language-learning conversation practice, hands-free content reading, and accessibility-focused audio content. It also describes examples involving Finnish language exercises and recipe instructions. ### Source excerpt News, tutorials, and updates from the Firebase team. ## From AI Agent to Human Agent: ElevenLabs Call Handoffs with Twilio DevFeed: [From AI Agent to Human Agent: ElevenLabs Call Handoffs with Twilio]() Original publisher: [Read original article]() Author: Ricardo Bangueses Published: 2026-09-09T00:00:00Z Content type: tutorial Language: en Sources: [Twilio Blog]() Topics: [Conversational AI](), [voice ai](), [interoperability]() Tags: [ai-agent](), [developer-insights](), [how-to](), [integration](), [interoperability](), [voice]() ### AI overview This tutorial explains how to integrate an ElevenLabs voice agent with Twilio Programmable Voice so the agent can escalate an active call to human-agent routing while preserving call control and useful context. The example uses Twilio Flex as the destination. ### Source excerpt Learn how to integrate an ElevenLabs voice agent with Twilio Programmable Voice for seamless AI-to-human call handoffs, preserving context and call control. ## 🍔🧠 How OpenAI Built GPT-Live for Low-Latency Voice AI DevFeed: [🍔🧠 How OpenAI Built GPT-Live for Low-Latency Voice AI]() Original publisher: [Read original article]() Author: Alexandre Zajac Published: 2026-09-07T15:31:33Z Content type: article Language: en Sources: [Hungry Minds]() Topics: [Conversational AI](), [Low Latency](), [voice ai](), [OpenAI](), [real-time](), [Streaming](), [Remote Procedure Call (RPC)](), [Go]() Tags: [go](), [low-latency](), [openai](), [real-time](), [rpc](), [software-engineering](), [streaming](), [voice-ai]() ### AI overview The article explains how OpenAI built GPT-Live as a low-latency, full-duplex voice system. It describes a fast audio path that listens and speaks simultaneously, asynchronous delegation of deeper reasoning and backend work, stateful handoffs, optimized protocol boundaries, and a Go-based media frontend. ### Source excerpt PLUS: Zero-knowledge proofs ⚡, Design.md agent automation 👨💻, System Design Docs 101 📚 ## Intelligent transcription with Gemini 3.5 Transcribe DevFeed: [Intelligent transcription with Gemini 3.5 Transcribe]() Original publisher: [Read original article]() Author: Diego Melendo Casado Published: 2026-08-26T17:01:00Z Content type: release Language: en Sources: [Google DeepMind News]() Topics: [asr](), [voice ai](), [Google AI](), [API](), [real-time](), [Streaming](), [Latency](), [Artificial Intelligence]() Tags: [ai](), [analysis](), [analytics](), [android](), [api](), [audio](), [developer](), [developers](), [gemini](), [google](), [google-ai](), [latency](), [macos](), [model](), [none](), [real-time](), [speech](), [streaming](), [transcription](), [voice](), [workflows]() ### AI overview Google introduces Gemini 3.5 Transcribe, a speech-to-text model for accurate, formatted transcription in noisy and specialized audio. Developers can use it through the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform for voice agents, real-time captioning, and post-call analytics. It supports real-time streaming and pre-recorded audio processing, custom vocabulary, speaker attribution, word-level timestamps, and more than 85 languages. ### Source excerpt Now you can get more intelligent speech-to-text transcription with Gemini 3.5 Transcribe. ## Fish Audio models now available on Vercel AI Gateway for free DevFeed: [Fish Audio models now available on Vercel AI Gateway for free]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-08-19T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [voice ai](), [Vercel](), [asr](), [Streaming](), [Low Latency](), [SDKs]() Tags: [ai-gateway](), [audio](), [browser](), [free](), [launch](), [models](), [sdk](), [speech](), [streaming](), [text-to-speech](), [transcription](), [voice]() ### AI overview Fish Audio's text-to-speech and transcription models are available on Vercel AI Gateway. The models are free for 30 days, with AI SDK 7 support for speech generation and transcription, including timestamped segments and word-level timing. ### Source excerpt Fish Audio's audio models are now available on AI Gateway. To celebrate the launch, every Fish Audio model is free on AI Gateway for the next 30 days, through September 18. Capability Regular Through September 18 Text-to-speech $15.00 per million characters Free Speech-to-text $0.36 per hour of audio Free Four models from Fish Audio are available, including their latest text-to-speech model: fish-audio/s2.1-pro (text-to-speech): Built for low-latency streaming; clones a voice from a reference recording. fish-audio/transcribe-1 (transcription): Returns the text along with the duration of the audio and timestamped segments, down to individual words. fish-audio/s2-pro (text-to-speech): Covers around eighty languages and takes inline tags, plain-language directions written into the text itself, so you can change how a single word or phrase is delivered instead of setting one style for the whole request. fish-audio/s1 (text-to-speech): Reads text that can carry markers for emotion, tone, and sound effects. How to use models during the offer period Using the standard model name (i.e., fish-audio/s2.1-pro) is free, but will automatically begin billing when the offer period ends. To ensure you aren't billed after the free period, add the -free suffix to the standard name, and the model will stop serving when the offer ends (i.e., fish-audio/s2.1-pro-free). Speech and transcription ship in the current AI SDK 7 release. Text-to-speech Generate spoken audio from text with generateSpeech and write the result: Speech-to-text Transcribe recordings into text with transcribe. The audio can be a buffer, a base64 string, or a URL: Each segment carries the text and its start and end time in seconds, down to individual words. Playground You can also try the Fish Audio models without writing any code. Open the models list, click into a model, and send text or audio to hear or read the result in your browser. For a full overview of how to utilize audio models, refer to the speech quickst ## Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS DevFeed: [Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS]() Original publisher: [Read original article]() Author: Maryam Motamedi; Mikyas Desta; Jason Li; Jason Roche Published: 2026-08-10T16:25:36Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Low Latency](), [Latency](), [voice ai](), [NVIDIA NIM](), [Open Source Models & Datasets](), [asr](), [Conversational AI](), [Large Language Model](), [Automation]() Tags: [agents](), [ai](), [api](), [audio](), [automation](), [conversational-ai](), [data](), [developers](), [infrastructure](), [latency](), [llm](), [low-latency](), [model](), [models](), [nvidia](), [nvidia-nim](), [open](), [speech](), [text-to-speech](), [voice]() ### AI overview This developer article presents NVIDIA Magpie Multilingual TTS as an open-weights, 364M-parameter text-to-speech model for building low-latency multilingual voice applications. It explains how a self-managed cascaded ASR, TTS, and LLM architecture can provide deployment control, tuning, privacy, and predictable performance across 12 languages. ### Source excerpt Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS Every voice interaction has a latency budget. By the time a user hears your application respond, you've already spent precious milliseconds capturing audio, transcribing speech, running an LLM, retrieving context, and generating a response. Text-to-speech (TTS) is the final step -- and the one users notice most. If speech generation is slow, the whole experience feels slow. ## How we built a realtime system for responsive voice AI in six months DevFeed: [How we built a realtime system for responsive voice AI in six months]() Original publisher: [Read original article]() Published: 2026-08-03T07:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [voice ai](), [Low Latency](), [Inference](), [model-deployment](), [systems](), [Artificial Intelligence]() Tags: [agents](), [ai](), [architecture](), [audio](), [chatgpt](), [engineering](), [gpt](), [inference](), [latency](), [llm](), [llms](), [low-latency](), [model](), [speech](), [systems](), [text-to-speech](), [voice](), [voice-ai]() ### AI overview OpenAI describes GPT-Live, a full-duplex voice system designed for continuous, natural conversation. Its low-latency architecture streams audio in both directions, separates asynchronous delegation from the core voice path, and coordinates stateful inference, dynamic context management, and protocol-level optimization. ### Source excerpt GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations. ## Building AI Features in Kotlin Multiplatform Apps with Local Prompt Iteration DevFeed: [Building AI Features in Kotlin Multiplatform Apps with Local Prompt Iteration]() Original publisher: [Read original article]() Author: Paul Woitaschek Published: 2026-07-17T11:49:08Z Content type: tutorial Language: en Sources: [Stories by Paul Woitaschek on Medium]() Topics: [Kotlin Multiplatform](), [LLMs](), [Mobile](), [API](), [Back end](), [voice ai](), [anthropic](), [OpenAI]() Tags: [ai](), [anthropic](), [api](), [backend](), [kotlin](), [kotlin-multiplatform](), [llm](), [llms](), [mobile](), [mobile-app-development](), [openai](), [speech](), [voice]() ### AI overview This tutorial presents a workflow for building AI features in Kotlin Multiplatform mobile apps. It recommends defining the app interface first, implementing the feature locally with Koog to iterate quickly on prompts, and moving the implementation to a backend once the output is reliable. The example uses natural-language and voice-based nutrition tracking, with LLM output converted into proposed structured actions. ### Source excerpt TLDR: Define the interface in the app, iterate locally with Koog, move the logic to the backend when it's done. AI features have a weird reputation among mobile developers. The model sits behind an API, the prompt lives on a server someone else owns, and every change means a ticket, a review, a deploy. So the whole topic feels like backend territory. But an AI feature is just a feature. Text in, structured data out, some logic in between. The only unusual part: the core of that logic is a prompt. And prompts are not designed, they are iterated. You try an input, look at the output, adjust, try again. Dozens of times. So the real problem is not building the feature. It's making that loop fast. The pattern I would like to show: define an interface in the app, build the real UI against it, implement it locally with Koog, iterate until the output is solid, then move the implementation to the backend. In Kotlin that last step is mostly copy paste. The example: track everything in one sentence We build Yazio, a nutrition tracking app, as Kotlin Multiplatform: one shared codebase for iOS and Android. That matters here, because everything below is written once and runs on both platforms. Tracking today is many small interactions: search a food, pick a portion, add water, log a workout. Now imagine the user just says what happened: "I had two scrambled eggs and a coffee for breakfast, drank half a liter of water, went for a 30 minute run, and for lunch I ate the same as yesterday."Users can track using voice The app answers with a list of proposed actions. The user deletes the wrong ones, speaks again to add what's missing, and confirms everything at once. Speech to text is solved on both platforms, so from our side the input is just a string. Messy natural language in, exact typed data out. That's what LLMs are good at. It's also the kind of logic you won't get right on the first try. The constraint: the key can't live in the app You can't ship an OpenAI or Anthropic API ke ## ChatGPT Live and the New Architecture of Voice AI DevFeed: [ChatGPT Live and the New Architecture of Voice AI]() Original publisher: [Read original article]() Author: RisingStack Engineering Published: 2026-07-16T12:38:22Z Content type: article Language: en Sources: [RisingStack]() Topics: [voice ai](), [Artificial Intelligence](), [ChatGPT](), [OpenAI](), [systems]() Tags: [ai](), [architecture](), [audio](), [chatgpt](), [engineering](), [gpt](), [here](), [interrupt](), [messages](), [models](), [openai](), [quality](), [speaking](), [speech](), [systems](), [talk](), [tool](), [update](), [voice-ai](), [voices]() ### AI overview The article explains how OpenAI's GPT-Live models power ChatGPT Voice through a full-duplex architecture. The system can listen and speak simultaneously, handle interruptions, pause while users think, and delegate deeper reasoning, web search, or other complex work to another model. ### Source excerpt OpenAI has introduced GPT-Live, a new generation of voice models that now powers ChatGPT Voice. At first, this may sound like another voice-quality update. The voices have been remastered, ChatGPT should interrupt less often, and it can respond more naturally when you pause, change direction or speak over it. But GPT-Live is more than a [...] The post ChatGPT Live and the New Architecture of Voice AI appeared first on RisingStack Engineering. ## Introducing Real World VoiceEQ: Measuring the human quality of voice AI DevFeed: [Introducing Real World VoiceEQ: Measuring the human quality of voice AI]() Original publisher: [Read original article]() Author: David Ayllon; Alice; Jeff Brooks; Franc Camps Febrer; Jakub Piotr Cłapa; Theo Lebryk; Jens Madsen; Olya Ossipova; Sharath Rao; Hoon Shin Published: 2026-07-15T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [voice ai](), [Benchmark](), [Human-AI evaluation](), [Artificial Intelligence](), [asr](), [human feedback](), [Open Source]() Tags: [ai](), [announcement](), [audio](), [benchmark](), [benchmarks](), [evaluation](), [human-feedback](), [leaderboard](), [open-source](), [reinforcement-learning](), [speech](), [voice-ai]() ### AI overview Real World VoiceEQ is a benchmark for evaluating the human quality of voice AI beyond latency and word error rate. It measures how voice systems recognize, produce, and respond to acoustic information such as tone, emotion, speaker identity, and background context across ASR, TTS, speech-to-speech, and speech understanding. The benchmark covers more than 40 voice models, 15+ evaluation dimensions, and more than 60 metrics, using over 1 million human ratings. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Hugging Face and Cerebras bring Gemma 4 to real-time voice AI DevFeed: [Hugging Face and Cerebras bring Gemma 4 to real-time voice AI]() Original publisher: [Read original article]() Author: Amir Mahla; Andres Marafioti; Leandro von Werra; Saurabh Vyas Published: 2026-07-01T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [voice ai](), [gemma4](), [hugging face](), [Artificial Intelligence](), [Open Source](), [real-time](), [Low Latency](), [Inference](), [Conversational AI](), [Language models](), [systems]() Tags: [ai](), [audio](), [gemma](), [hugging-face](), [inference](), [inference-providers](), [latency](), [low-latency](), [model](), [models](), [multimodal](), [open-source](), [open-source-collab](), [partnerships](), [performance](), [real-time](), [systems](), [text-to-speech](), [voice](), [voice-ai]() ### AI overview Hugging Face and Cerebras present a real-time speech-to-speech pipeline that combines Cerebras inference, Google DeepMind's Gemma 4 31B language model, and Qwen text-to-speech. The modular, open architecture is designed for low latency, predictable performance, and adaptable voice experiences across assistants, robots, products, and research projects. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Realtime voice, speech, and transcription now supported on AI Gateway DevFeed: [Realtime voice, speech, and transcription now supported on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-06-29T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [real-time](), [voice ai](), [vercel ai sdk](), [Artificial Intelligence](), [SDKs](), [WebSocket](), [browser](), [Low Latency](), [API keys](), [observability](), [App]() Tags: [agent](), [ai](), [api](), [app](), [audio](), [browser](), [code](), [documentation](), [latency](), [low-latency](), [playground](), [real-time](), [sdk](), [speech](), [transcription](), [voice]() ### AI overview AI Gateway adds beta support for realtime voice and audio models through AI SDK 7, enabling voice agents, text-to-speech, and speech-to-text. Developers can use the realtime example, quickstart, or browser playground, with observability, spend controls, bring-your-own-key support, and no markup or platform fees. ### Source excerpt AI Gateway now supports voice and audio models. You can build realtime voice agents, generate speech from text, and transcribe audio to text. This provides the same observability, spend controls, and bring-your-own-key support as text, image, and video models in AI Gateway, with no markup or platform fees. These capabilities are in beta and available via AI SDK 7. With realtime support, a single model takes audio in and audio out, so a user can talk and hear a reply back in near real time instead of waiting on a chain of separate models. Capability What it does Realtime voice agents Model listens to the user, works out a response, and speaks it back in a live, low-latency conversation. It can call your tools mid-conversation to look something up or take an action. The useRealtime hook handles microphone capture and playback. Text to speech Generate spoken audio from text, with a selectable voice and output format such as MP3. Use it for voiceovers, audio versions of written content, and spoken responses. Speech to text Transcribe recordings into text, from a file buffer, base64 string, or URL. Use it for voice notes or other transcriptions. Two ways to get started: Follow the realtime example below or the realtime quickstart to add a voice agent to your app. Use the playground. Talk to a realtime model in the browser, no code required, in the AI Gateway Playground. Realtime example A voice agent has two pieces: a server route that mints a short-lived token, so your API key never reaches the client, and a browser component that connects with it. Add the token route: Then connect from the browser. The useRealtime hook fetches that route and manages the WebSocket connection, microphone capture, and audio playback: Playground You can also try audio models without writing any code. Open the models page, click into a model, and interact with it right in the browser: Talk to a realtime model to hold a voice conversation Send text and have a transcription model read it back ## xAI Grok audio models now available on Vercel AI Gateway DevFeed: [xAI Grok audio models now available on Vercel AI Gateway]() Original publisher: [Read original article]() Author: Carlton Aikins Published: 2026-06-29T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [vercel ai sdk](), [voice ai](), [Artificial Intelligence](), [SDKs](), [API](), [WebSocket](), [Vercel](), [React](), [browser]() Tags: [ai](), [ai-gateway](), [api](), [audio](), [browser](), [models](), [observability](), [react](), [release](), [responses](), [routing](), [sdk](), [server](), [speech](), [text-to-speech](), [vercel](), [voice]() ### AI overview xAI Grok audio models are now available through Vercel AI Gateway and the AI SDK 7 release. The integration supports realtime voice, text-to-speech, and speech-to-text, with routing, observability, and spend controls. ### Source excerpt xAI's audio models are now live on AI Gateway. Realtime voice, text to speech, and speech to text are all available through the AI SDK with the same routing, observability, and spend controls as your other models. These capabilities are available on the AI SDK 7 release. Available models Capability Models Realtime voice xai/grok-voice-think-fast-1.0 Text to speech xai/grok-tts Speech to text xai/grok-stt Realtime A voice agent has two pieces: a server route that mints a short-lived token, so your API key never reaches the client, and a browser component that connects with it. Add the token route: this example sets model to xai/grok-voice-think-fast-1.0: Then connect from the browser. The useRealtimehook from @ai-sdk/react fetches that route and manages the WebSocket connection, microphone capture, and audio playback: Text to speech Generate spoken audio from text with generateSpeech. Pass a voice and an output format, then write the result to a file with xai/grok-tts: Speech to text Transcribe recordings into text with transcribe. This example uses xai/grok-stt: Playground You can also try the xAI audio models directly in the AI Gateway playground. Open the models list and click into any of the models to use them directly in the browser. The xai/grok-voice-think-fast-1.0 playground here allows you to talk to the agent and see responses instantly: More information Realtime quickstart Speech quickstart See all xAI models Read more ## How Dream11 Built a Real-Time AI Sports Streaming Companion DevFeed: [How Dream11 Built a Real-Time AI Sports Streaming Companion]() Original publisher: [Read original article]() Author: Dream Blog Published: 2026-06-15T09:51:14Z Content type: tutorial Language: en Sources: [Dream11 Engineering]() Topics: [AI Agent](), [Streaming](), [Artificial Intelligence](), [real-time](), [voice ai](), [Sports]() Tags: [agent](), [ai](), [ai-agent](), [creators](), [cricket](), [latency](), [real-time](), [sports](), [streaming](), [tech](), [voice](), [voice-ai]() ### AI overview This developer article describes Dream11's AI Companion, a multilingual voice AI agent that joins live creator streams as a co-host. It explains that the system watches matches, reacts to events, interacts with creators and audiences, hosts trivia, and supports live cricket commentary with approximately two-second voice latency. ### Source excerpt Written by Narayan Sharma, Rajesh Mohanty, Dhruv Nigam, Chetna Meena and Palash TatteThe Moment That Sparked Everything Picture this: a live cricket stream. A boundary flies to the fence. The creator reacts; screaming, laughing, and enjoying the moment. The audience piles on in the chat. And in the corner of the screen, a street-smart monkey named Googly Bhai mutters: "Bhai kya cover drive mara Kohli ne, ball field pe aise glide kar rahi hai jaise garam parathe pe makkan!" The audience erupts. Not because it was scripted. Not because a human typed it. But because AI watched the same ball, processed the same moment, and reacted, with personality, with timing, and with an opinion, in under two seconds. That's the Dream11 AI Companion. And building it was anything but simple. 🏆 World's first real-time AI sports streaming companion ⚡ ~2 second end-to-end voice latency 🗣 70+ languages supported natively by S2S model; primary: Hindi, English, Hinglish 🔌 Zero extra setup for streamers -- integrates directly via OBS + Creator Console What We Set Out to Build With 250M+ users, Dream11 has been on a journey to become everyone's sports entertainment destination. And entertainment lives where the fans are; inside live streams, creator channels, match-day conversations. The question we asked ourselves: What if a creator never had to stream alone again? Or if they were unavailable, could we ensure they had a back up? The answer was an AI Companion: A real-time, multilingual voice AI agent that joins live creator streams as a co-host. It watches the match. It reacts to what's happening. It banters with creators and audiences. It hosts trivia. It roasts players. It debates cricket. Meet the Characters Before we get into architecture, meet the two AI characters at the heart of this product. Bittu Bindas 🐻 A bold, banterous bear. Speaks Hindi (in Mumbaikar style). Playful, opinionated, and absolutely no-filter. Bittu doesn't overthink. He just says what every fan in the room is think ## Advancing voice intelligence with new models in the API DevFeed: [Advancing voice intelligence with new models in the API]() Original publisher: [Read original article]() Published: 2026-05-07T10:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [API](), [voice ai](), [OpenAI](), [Artificial Intelligence](), [asr](), [Streaming](), [Whisper]() Tags: [agent](), [api](), [audio](), [developers](), [launch](), [model](), [models](), [openai](), [product](), [real-time](), [speech](), [streaming](), [tools](), [voice](), [voice-ai](), [whisper]() ### AI overview OpenAI is introducing three audio models in its API: GPT-Realtime-2 for more capable conversational voice interactions, GPT-Realtime-Translate for live speech translation, and GPT-Realtime-Whisper for streaming speech-to-text. The models are designed to support voice applications that can listen, reason, translate, transcribe, use tools, and take action in real time. ### Source excerpt Explore new realtime voice models in the OpenAI API that can reason, translate, and transcribe speech, enabling more natural and intelligent voice experiences. ## How OpenAI delivers low-latency voice AI at scale DevFeed: [How OpenAI delivers low-latency voice AI at scale]() Original publisher: [Read original article]() Published: 2026-05-04T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [voice ai](), [WebRTC](), [Artificial Intelligence](), [OpenAI](), [Latency](), [Low Latency](), [real-time](), [API](), [browsers](), [client](), [ChatGPT](), [Server]() Tags: [ai](), [api](), [audio](), [browsers](), [chatgpt](), [engineering](), [global](), [latency](), [low-latency](), [network](), [openai](), [real-time](), [server](), [servers](), [speech](), [speed](), [voice-ai](), [webrtc]() ### AI overview OpenAI describes a rearchitected WebRTC stack for delivering low-latency voice AI at global scale. The article explains how split relay and transceiver components address connection setup, stateful media sessions, routing, and stable media round-trip performance while preserving standard WebRTC behavior for clients. ### Source excerpt How OpenAI rebuilt its WebRTC stack to power real-time Voice AI with low latency, global scale, and seamless conversational turn-taking. [Next page]()