# livekit

LiveKit is an open-source framework and cloud platform for building realtime voice, video, and physical AI agents, with WebRTC infrastructure, SDKs, and APIs.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How to Build a Voice AI Agent

DevFeed: [How to Build a Voice AI Agent](<https://devfeed.tech/articles/how-to-build-a-voice-ai-agent-129101.md>)

Original publisher: [Read original article](<https://openrouter.ai/blog/tutorials/build-voice-ai-agent/>)

Author: OpenRouter

Published: 2026-11-10T00:00:00Z

Content type: tutorial

Language: en

Sources: [OpenRouter](<https://devfeed.tech/sources/openrouter.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [Tutorial](<https://devfeed.tech/topics/tutorial.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [build](<https://devfeed.tech/tags/build.md>), [call](<https://devfeed.tech/tags/call.md>), [generate](<https://devfeed.tech/tags/generate.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [tools](<https://devfeed.tech/tags/tools.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

### AI overview

The tutorial builds a Python restaurant booking voice agent using OpenRouter for transcription (ElevenLabs Scribe v2), tool-calling and replies (GPT-6 Luna), and speech generation (ElevenLabs Flash v2.5). It transcribes callers, checks availability and books through mock tools, then streams completed reply sentences to TTS; LiveKit Agents adds live audio, voice activity detection, playback, and interruption handling. In tests, server-side time to first audio had a 1.9-second median overall (1.4 seconds without tools, 2.4 with tools), excluding network and playback delays; the example's extra LLM requests can make it slower. TTS made up about 90% of measured model cost. Scribe v2 was chosen for its accuracy-speed balance, though recognizers often miss uncommon names, so callers should confirm key details. The tutorial stresses replacing mock tools with a backend that verifies successful actions, testing with representative speech, and measuring end-to-end latency. Separate speech-to-speech tests confirmed tool selection but did not measure full conversation speed or quality.

### Source excerpt

A voice agent needs to do more than generate a good answer. It must understand what someone said, decide what to do, call any needed tools, and start speaking again before the pause gets awkward.

## AssemblyAI Ships AssemblyAI-TTS-1: A $15 per 1M Character Text-to-Speech API for Voice Agents

DevFeed: [AssemblyAI Ships AssemblyAI-TTS-1: A $15 per 1M Character Text-to-Speech API for Voice Agents](<https://devfeed.tech/articles/assemblyai-ships-assemblyai-tts-1-a-15-per-1m-character-text-to-speech-api-for-voice-agents-106113.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/10/29/assemblyai-tts-1-text-to-speech-api-voice-agents/>)

Author: Michal Sutter

Published: 2026-10-29T07:28:36Z

Content type: release

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [asr](<https://devfeed.tech/topics/asr.md>), [livekit](<https://devfeed.tech/topics/livekit.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [assemblyai](<https://devfeed.tech/tags/assemblyai.md>), [audio-language-model](<https://devfeed.tech/tags/audio-language-model.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [costs](<https://devfeed.tech/tags/costs.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-developers](<https://devfeed.tech/tags/for-developers.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [languages](<https://devfeed.tech/tags/languages.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [launch](<https://devfeed.tech/tags/launch.md>), [model](<https://devfeed.tech/tags/model.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [speech](<https://devfeed.tech/tags/speech.md>), [staff](<https://devfeed.tech/tags/staff.md>), [technology](<https://devfeed.tech/tags/technology.md>), [text-to-speech](<https://devfeed.tech/tags/text-to-speech.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

### AI overview

AssemblyAI-TTS-1 is a hosted streaming TTS API for live voice agents, priced at $15 per 1M input characters with unlimited concurrency and no contract. It supports HTTP, WebSocket, and an OpenAI-compatible route, six launch languages, voice cloning with speaker permission, and telephony audio formats; it runs only in AssemblyAI's US or EU cloud, with no open weights or on-prem option. AssemblyAI reports 93.7% entity accuracy and 47 ms median time to first byte in its own tests, while Cekura measured 159 ms streaming latency and 81.5% reading accuracy. Inworld TTS-2 Flash also lists $15 per 1M on demand, but its cited tier allows five concurrent requests. At launch, TTS-1 lacks SSML, speed controls, pronunciation dictionaries, and emotion tags.

### Source excerpt

AssemblyAI has released AssemblyAI-TTS-1, its first text-to-speech model for voice agents. It costs $15 per 1M characters, offers unlimited concurrency without a contract, and supports 6 languages at launch. The post AssemblyAI Ships AssemblyAI-TTS-1: A $15 per 1M Character Text-to-Speech API for Voice Agents appeared first on MarkTechPost.

## Mistral AI Releases Voxtral 3: Speech-to-Text, TTS and a Voice Agent SDK

DevFeed: [Mistral AI Releases Voxtral 3: Speech-to-Text, TTS and a Voice Agent SDK](<https://devfeed.tech/articles/mistral-ai-releases-voxtral-3-speech-to-text-tts-and-a-voice-agent-sdk-91855.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/10/20/mistral-voxtral-3-speech-models-voice-agent-sdk/>)

Author: Asif Razzaq

Published: 2026-10-21T06:03:12Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [voice ai](<https://devfeed.tech/topics/voice-ai.md>), [asr](<https://devfeed.tech/topics/asr.md>), [Speech Processing](<https://devfeed.tech/topics/speech-processing.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [SDK](<https://devfeed.tech/topics/sdk.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Whisper](<https://devfeed.tech/topics/whisper.md>), [machine-translation](<https://devfeed.tech/topics/machine-translation.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [asr](<https://devfeed.tech/tags/asr.md>), [audio-language-model](<https://devfeed.tech/tags/audio-language-model.md>), [diarization](<https://devfeed.tech/tags/diarization.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [livekit](<https://devfeed.tech/tags/livekit.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mistral-ai](<https://devfeed.tech/tags/mistral-ai.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [releases](<https://devfeed.tech/tags/releases.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [speech](<https://devfeed.tech/tags/speech.md>), [speech-to-text](<https://devfeed.tech/tags/speech-to-text.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [tts](<https://devfeed.tech/tags/tts.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

### AI overview

Voxtral 3 bundles three transcription models, Voxtral Speech 3 for text-to-speech, and a LiveKit-based voice-agent SDK; the models are in public preview on Mistral's API. Small Transcribe 3 scores 2.1% AA-WER (#3 on Artificial Analysis) and 18.4% cpWER for diarization, while Mini is a 4B, lower-cost batch option. All transcription models support diarization and context biasing; batch transcription covers 50 languages. The SDK streams speech recognition, LLM reasoning and tool calls, then speech generation, supports caller interruption and SIP or WebRTC sessions, and allows swapping its component models. Realtime transcription trades accuracy for latency: at 240 ms it scores 7.4% WER, versus 4.2% for Gemini 3.5 Realtime Transcribe. Listed prices range from $0.0035-$0.008 per transcription minute; TTS is $13 per million characters. The article reports that GPU requirements are undisclosed and no open weights were announced.

### Source excerpt

Mistral AI released Voxtral 3, a family of 3 transcription models, 1 text-to-speech model and a LiveKit-based voice agent SDK. Voxtral Small Transcribe 3 scores 2.1% AA-WER, ranking #3 on Artificial Analysis. The post Mistral AI Releases Voxtral 3: Speech-to-Text, TTS and a Voice Agent SDK appeared first on MarkTechPost.

## Petal: Open-Source Screen Sharing You Can Self-Host

DevFeed: [Petal: Open-Source Screen Sharing You Can Self-Host](<https://devfeed.tech/articles/petal-open-source-screen-sharing-you-can-self-host-91224.md>)

Original publisher: [Read original article](<https://noted.lol/petal/>)

Author: Jeremy

Published: 2026-10-20T16:06:04Z

Content type: article

Language: en

Sources: [Noted](<https://devfeed.tech/sources/noted.md>)

Topics: [livekit](<https://devfeed.tech/topics/livekit.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [access-tokens](<https://devfeed.tech/tags/access-tokens.md>), [ai](<https://devfeed.tech/tags/ai.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [audio](<https://devfeed.tech/tags/audio.md>), [backend](<https://devfeed.tech/tags/backend.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [control](<https://devfeed.tech/tags/control.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [media](<https://devfeed.tech/tags/media.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [petal](<https://devfeed.tech/tags/petal.md>), [remote](<https://devfeed.tech/tags/remote.md>), [screen-sharing](<https://devfeed.tech/tags/screen-sharing.md>), [self-host](<https://devfeed.tech/tags/self-host.md>), [server](<https://devfeed.tech/tags/server.md>), [setup](<https://devfeed.tech/tags/setup.md>)

### AI overview

Petal places each participant's shared desktop window on the other person's desktop, where it can be moved and kept beside their own work. It supports multiple windows, pointers, temporary drawings, and permission-based remote control; browser participants can join without installing the desktop app. Petal uses LiveKit, which can be hosted by the project or run on your own infrastructure. Self-hosting requires a reachable LiveKit server, a separate token-issuing backend (Vercel is the documented target, with compatible adapters possible), and a desktop client built with the backend address configured. The project is pre-1.0: macOS is more mature, Windows is incomplete, Linux support is planned, and remote control is early. An optional Gemini feature can be disabled.

### Source excerpt

Petal lets remote collaborators share movable desktop windows and run their own media server, although setup is still hands-on.

## Voxtral 3

DevFeed: [Voxtral 3](<https://devfeed.tech/articles/voxtral-3-91117.md>)

Original publisher: [Read original article](<https://mistral.ai/news/voxtral-3/>)

Published: 2026-10-20T12:00:22Z

Content type: release

Language: en

Sources: [Mistral AI](<https://devfeed.tech/sources/mistral-ai-blog.md>)

Topics: [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [WebRTC](<https://devfeed.tech/topics/webrtc.md>), [Whisper](<https://devfeed.tech/topics/whisper.md>), [private cloud](<https://devfeed.tech/topics/private-cloud.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [deep](<https://devfeed.tech/tags/deep.md>), [eu](<https://devfeed.tech/tags/eu.md>), [languages](<https://devfeed.tech/tags/languages.md>), [mistral](<https://devfeed.tech/tags/mistral.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [speech](<https://devfeed.tech/tags/speech.md>), [time](<https://devfeed.tech/tags/time.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>), [transcription](<https://devfeed.tech/tags/transcription.md>), [tts](<https://devfeed.tech/tags/tts.md>), [voice](<https://devfeed.tech/tags/voice.md>)

### AI overview

Voxtral 3 combines speech models with a LiveKit-based SDK that streams transcription, reasoning and tool use, and speech generation in one voice-agent pipeline. Its transcribe models support over 50 languages, diarization, and context biasing; the realtime variant reports sub-500 ms latency in over 35 languages and end-of-turn prediction. Mini TTS supports 35+ languages and 50+ dialects, with contextual emotion, pacing, and emphasis. Agents can call tools, search the web, retrieve from connected systems, and communicate over SIP or WebRTC. Each stage uses a separate model, allowing the LLM, voice, or language to be changed independently. Voxtral is offered through Mistral-hosted endpoints, including EU hosting, or for deployment on customer infrastructure; the text says organizations can control audio retention. The article states prices of $0.0035/min for Mini batch transcription, $0.008/min for realtime transcription, and $13 per million TTS characters. These are product claims in the supplied text.

### Source excerpt

Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages -- accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.

## Augment Your LiveKit Agent with Modal GPUs

DevFeed: [Augment Your LiveKit Agent with Modal GPUs](<https://devfeed.tech/articles/augment-your-livekit-agent-with-modal-gpus-97784.md>)

Original publisher: [Read original article](<https://modal.com/blog/livekit-modal>)

Author: Andrew Hinh

Published: 2026-10-15T12:00:00Z

Content type: tutorial

Language: en

Sources: [Modal](<https://devfeed.tech/sources/modal.md>)

Topics: [livekit](<https://devfeed.tech/topics/livekit.md>), [sessions](<https://devfeed.tech/topics/sessions.md>)

Tags: [affinity](<https://devfeed.tech/tags/affinity.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [apis](<https://devfeed.tech/tags/apis.md>), [applications](<https://devfeed.tech/tags/applications.md>), [audio](<https://devfeed.tech/tags/audio.md>), [avatar](<https://devfeed.tech/tags/avatar.md>), [container](<https://devfeed.tech/tags/container.md>), [custom](<https://devfeed.tech/tags/custom.md>), [docs](<https://devfeed.tech/tags/docs.md>), [expression](<https://devfeed.tech/tags/expression.md>), [frameworks-and-tools](<https://devfeed.tech/tags/frameworks-and-tools.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [livekit](<https://devfeed.tech/tags/livekit.md>), [modal](<https://devfeed.tech/tags/modal.md>), [models](<https://devfeed.tech/tags/models.md>), [open-weights](<https://devfeed.tech/tags/open-weights.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [sticky-sessions](<https://devfeed.tech/tags/sticky-sessions.md>)

### AI overview

The excerpt describes running BitHuman's open-weights video avatar with Qwen3-TTS through LiveKit Agents on Modal GPUs. LiveKit's BitHuman integration uses a self-hosted GPU container with a `/launch` endpoint that starts the avatar and joins a LiveKit room. Because the endpoint returns as soon as the avatar joins, the article uses Modal Sticky Sessions to keep the container available across client-side session start and end, and let WebSocket connections reconnect to the same container. The agent starts a session when a participant joins, passes its token to `/launch`, and ends the session when the call completes. GPU snapshots hide cold starts that would otherwise require reloading gigabytes of model weights. The supplied text is an excerpt and does not include the referenced full code.

### Source excerpt

How to run a LiveKit video avatar with open-weights models on Modal GPUs, using Sticky Sessions for container affinity.

## How a Public Voice AI Demo Enabled Toll Fraud, and How to Secure It

DevFeed: [How a Public Voice AI Demo Enabled Toll Fraud, and How to Secure It](<https://devfeed.tech/articles/my-voice-ai-demo-was-hit-by-a-982-traffic-pumping-attack-here-s-what-i-learned-66525.md>)

Original publisher: [Read original article](<https://www.twilio.com/en-us/blog/developers/best-practices/secure-voice-agent-demos>)

Author: Rishab Kumar

Published: 2026-10-06T00:00:00Z

Content type: article

Language: en

Sources: [Twilio](<https://devfeed.tech/sources/twilio-blog.md>), [Twilio Blog](<https://devfeed.tech/sources/twilio-blog-2.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [Vishing](<https://devfeed.tech/topics/vishing.md>), [twilio api](<https://devfeed.tech/topics/twilio-api.md>)

Tags: [alert](<https://devfeed.tech/tags/alert.md>), [attack](<https://devfeed.tech/tags/attack.md>), [developer-insights](<https://devfeed.tech/tags/developer-insights.md>), [fraud](<https://devfeed.tech/tags/fraud.md>), [twilio](<https://devfeed.tech/tags/twilio.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

### AI overview

A public Twilio Conversation Relay demo allowed attackers to trigger hundreds of unauthorized international calls, costing about $971.50 in Twilio usage and $10.58 in Google Gemini usage. The author traces the attack through call records, Azure logs, and speech transcripts, while noting that the evidence cannot identify who controlled the destination numbers or benefited. Recommended safeguards include endpoint authentication and authorization, call and cost limits, geographic restrictions, webhook signature validation, provider budgets, isolated demo environments, and careful logging.

### Source excerpt

See how a $982 voice AI toll fraud attack happened to my Twilio Voice demo and learn measures to secure a voice app. Understand patterns, preventive controls, more.

## Giving voice agents a voice that adapts to context

DevFeed: [Giving voice agents a voice that adapts to context](<https://devfeed.tech/articles/giving-voice-agents-a-voice-that-adapts-to-context-81247.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/voice-that-adapts-to-context>)

Author: Gradium

Published: 2026-09-29T00:00:00Z

Content type: tutorial

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [code](<https://devfeed.tech/tags/code.md>), [context-aware-voice](<https://devfeed.tech/tags/context-aware-voice.md>), [customer-support-agents](<https://devfeed.tech/tags/customer-support-agents.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [programmable-voice](<https://devfeed.tech/tags/programmable-voice.md>), [prompt-to-voice](<https://devfeed.tech/tags/prompt-to-voice.md>), [text-to-speech](<https://devfeed.tech/tags/text-to-speech.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-design](<https://devfeed.tech/tags/voice-design.md>), [voice-selection-pipeline](<https://devfeed.tech/tags/voice-selection-pipeline.md>)

### AI overview

A tutorial shows how to build a context-aware voice agent that classifies incoming messages, maps the signals to voice descriptions, and resolves requests to approved voices while creating missing voices in the background. It covers using a decision model, managing voice latency and voice libraries, and synthesizing replies with Gradium TTS.

### Source excerpt

Most voice agents speak with one preselected voice, whoever is on the line. Once a voice can be created from a text description, the voice becomes another property your code computes from context. This article builds the full pipeline: classify the message, map the signals to a Voice Design prompt, resolve it to an approved voice on the hot path, and design the missing ones in the background.

## Voice AI startup Modulate raises $25M to bring audio-native models to more developers

DevFeed: [Voice AI startup Modulate raises $25M to bring audio-native models to more developers](<https://devfeed.tech/articles/voice-ai-startup-modulate-raises-25m-to-bring-audio-native-models-to-more-developers-61066.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/09/28/voice-ai-startup-modulate-raises-25m-to-bring-audio-native-models-to-more-developers/>)

Author: Duncan Riley

Published: 2026-09-28T14:30:51Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [voice ai](<https://devfeed.tech/topics/voice-ai.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [open-llm-leaderboard](<https://devfeed.tech/topics/open-llm-leaderboard.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [audio-native-ai](<https://devfeed.tech/tags/audio-native-ai.md>), [carter-huffman](<https://devfeed.tech/tags/carter-huffman.md>), [deepfake](<https://devfeed.tech/tags/deepfake.md>), [developers](<https://devfeed.tech/tags/developers.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [ensemble-listening-model](<https://devfeed.tech/tags/ensemble-listening-model.md>), [funding](<https://devfeed.tech/tags/funding.md>), [future-ventures](<https://devfeed.tech/tags/future-ventures.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [hyperplane](<https://devfeed.tech/tags/hyperplane.md>), [lakestar](<https://devfeed.tech/tags/lakestar.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [massachusetts-institute-of-technology](<https://devfeed.tech/tags/massachusetts-institute-of-technology.md>), [mike-pappas](<https://devfeed.tech/tags/mike-pappas.md>), [modulate](<https://devfeed.tech/tags/modulate.md>), [news](<https://devfeed.tech/tags/news.md>), [open-asr-leaderboard](<https://devfeed.tech/tags/open-asr-leaderboard.md>), [speech-deepfake-arena](<https://devfeed.tech/tags/speech-deepfake-arena.md>), [steve-jurvetson](<https://devfeed.tech/tags/steve-jurvetson.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [transcription](<https://devfeed.tech/tags/transcription.md>), [trust-and-safety](<https://devfeed.tech/tags/trust-and-safety.md>), [velma](<https://devfeed.tech/tags/velma.md>), [velma-deepfake-detect](<https://devfeed.tech/tags/velma-deepfake-detect.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>)

### AI overview

Voice AI startup Modulate raised $25 million to expand access to its audio-native models, which analyze conversation signals such as emotion, intent, and possible deepfakes. Its Velma platform combines specialized models for uses including fraud detection, voice-agent monitoring, and moderation. The company plans new SDKs, APIs, industry-specific models, and hiring in research, engineering, and developer relations.

### Source excerpt

Voice artificial intelligence startup Modulate Inc. today announced it has raised $25 million in new funding to get its audio-native models in front of more developers. Modulate offers AI models that work on the raw audio of a conversation. Emotion, tone and intent all register as signals, as do signs that a voice is a [...] The post Voice AI startup Modulate raises $25M to bring audio-native models to more developers appeared first on SiliconANGLE.

## Gradium now available for free on LiveKit Inference

DevFeed: [Gradium now available for free on LiveKit Inference](<https://devfeed.tech/articles/gradium-now-available-for-free-on-livekit-inference-81236.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/livekit-gradium-partnership>)

Author: Gradium

Published: 2026-09-09T00:00:00Z

Content type: release

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [livekit](<https://devfeed.tech/topics/livekit.md>), [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [groq](<https://devfeed.tech/topics/groq.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [api](<https://devfeed.tech/tags/api.md>), [bill](<https://devfeed.tech/tags/bill.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [conversational-ai](<https://devfeed.tech/tags/conversational-ai.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [gradium](<https://devfeed.tech/tags/gradium.md>), [gradium-tts](<https://devfeed.tech/tags/gradium-tts.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [livekit](<https://devfeed.tech/tags/livekit.md>), [livekit-gradium](<https://devfeed.tech/tags/livekit-gradium.md>), [livekit-inference](<https://devfeed.tech/tags/livekit-inference.md>), [livekit-tts-provider](<https://devfeed.tech/tags/livekit-tts-provider.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [low-latency-tts](<https://devfeed.tech/tags/low-latency-tts.md>), [robust](<https://devfeed.tech/tags/robust.md>), [speech](<https://devfeed.tech/tags/speech.md>), [text-to-speech](<https://devfeed.tech/tags/text-to-speech.md>), [text-to-speech-for-voice-agents](<https://devfeed.tech/tags/text-to-speech-for-voice-agents.md>), [ttfa](<https://devfeed.tech/tags/ttfa.md>), [tts](<https://devfeed.tech/tags/tts.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-cloning](<https://devfeed.tech/tags/voice-cloning.md>)

### AI overview

Gradium Text-to-Speech is available through LiveKit Inference until Oct. 9 at no charge. The release describes support for voice cloning, conversational speech with low latency and robust pronunciation, and access through LiveKit without a separate Gradium account or API key. Gradium can be selected as the TTS provider for LiveKit voice agents, including through LiveKit's Agent Builder.

### Source excerpt

Gradium Text-to-Speech is now available on LiveKit Inference, free until Oct. 9. Gradium TTS is designed for conversational use cases, with voice cloning, low latency (below 250ms TTFA), and robust pronunciation on difficult cases.

## Launching Voice Design: prompt the voice your agent needs

DevFeed: [Launching Voice Design: prompt the voice your agent needs](<https://devfeed.tech/articles/launching-voice-design-prompt-the-voice-your-agent-needs-81235.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/launching-voice-design>)

Author: Gradium

Published: 2026-09-07T00:00:00Z

Content type: release

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [livekit](<https://devfeed.tech/topics/livekit.md>)

Tags: [ai-voice-generator](<https://devfeed.tech/tags/ai-voice-generator.md>), [apis](<https://devfeed.tech/tags/apis.md>), [custom-voices](<https://devfeed.tech/tags/custom-voices.md>), [product](<https://devfeed.tech/tags/product.md>), [prompt-to-voice](<https://devfeed.tech/tags/prompt-to-voice.md>), [regional-accents](<https://devfeed.tech/tags/regional-accents.md>), [synthetic-voices](<https://devfeed.tech/tags/synthetic-voices.md>), [text-to-speech](<https://devfeed.tech/tags/text-to-speech.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>), [voice-cloning-alternative](<https://devfeed.tech/tags/voice-cloning-alternative.md>), [voice-design](<https://devfeed.tech/tags/voice-design.md>)

### AI overview

Gradium's Voice Design feature creates synthetic voices from short text prompts for use in voice agents. The article describes its API and Studio workflow and presents a blind comparison across five languages, reporting that Gradium ranked first in each language among the tested systems.

### Source excerpt

Developers building voice agents ask us for voices matched to the use case in front of them: a Québécoise receptionist for a Montréal dealership, a Paulista support agent for a São Paulo fintech, a narrator in his sixties with the authority of a lecture hall. Briefs outnumber any catalog. Voice Design starts from a prompt: write one or two sentences, get complete new voices back in seconds, keep the one you want.

## Intelligent transcription with Gemini 3.5 Transcribe

DevFeed: [Intelligent transcription with Gemini 3.5 Transcribe](<https://devfeed.tech/articles/intelligent-transcription-with-gemini-3-5-transcribe-89439.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/>)

Author: Luke Leonhard

Published: 2026-08-26T17:00:00Z

Content type: release

Language: en

Sources: [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [asr](<https://devfeed.tech/topics/asr.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [livekit](<https://devfeed.tech/topics/livekit.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [audio](<https://devfeed.tech/tags/audio.md>), [chat](<https://devfeed.tech/tags/chat.md>), [developer-workflows](<https://devfeed.tech/tags/developer-workflows.md>), [feature](<https://devfeed.tech/tags/feature.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [none](<https://devfeed.tech/tags/none.md>), [transcription](<https://devfeed.tech/tags/transcription.md>)

### AI overview

Google introduces Gemini 3.5 Transcribe, a speech-to-text model available to developers through the Gemini API and Gemini Enterprise Agent Platform. It supports real-time streaming and recorded-audio transcription, with features including custom vocabulary, speaker attribution, word-level timestamps, and function calling. The release reports word error rates of 4.0% for streaming and 2.6% for non-streaming use cases, as measured by Artificial Analysis.

### Source excerpt

Text "Gemini 3.5 Transcribe" next to the Gemini spark, all on a blue background

## Gradium Extends Funding to $100 Million and Expands to Silicon Valley

DevFeed: [Gradium Extends Funding to $100 Million and Expands to Silicon Valley](<https://devfeed.tech/articles/gradium-extends-funding-to-100-million-and-expands-to-silicon-valley-81224.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/gradium-100-million-funding-nvidia>)

Author: Gradium

Published: 2026-07-08T00:00:00Z

Content type: news

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [twilio programmable video](<https://devfeed.tech/topics/twilio-programmable-video.md>)

Tags: [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [conversational-ai](<https://devfeed.tech/tags/conversational-ai.md>), [funding](<https://devfeed.tech/tags/funding.md>), [generative-audio](<https://devfeed.tech/tags/generative-audio.md>), [gradium-100-million](<https://devfeed.tech/tags/gradium-100-million.md>), [gradium-funding](<https://devfeed.tech/tags/gradium-funding.md>), [gradium-nvidia](<https://devfeed.tech/tags/gradium-nvidia.md>), [gradium-nvidia-investment](<https://devfeed.tech/tags/gradium-nvidia-investment.md>), [gradium-san-francisco-office](<https://devfeed.tech/tags/gradium-san-francisco-office.md>), [gradium-seed-round](<https://devfeed.tech/tags/gradium-seed-round.md>), [kyutai](<https://devfeed.tech/tags/kyutai.md>), [neil-zeghidour](<https://devfeed.tech/tags/neil-zeghidour.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [real-time-voice-ai](<https://devfeed.tech/tags/real-time-voice-ai.md>), [san-francisco](<https://devfeed.tech/tags/san-francisco.md>), [seed-funding](<https://devfeed.tech/tags/seed-funding.md>), [silicon-valley-expansion](<https://devfeed.tech/tags/silicon-valley-expansion.md>), [voice-ai](<https://devfeed.tech/tags/voice-ai.md>), [voice-ai-funding](<https://devfeed.tech/tags/voice-ai-funding.md>), [voice-ai-infrastructure](<https://devfeed.tech/tags/voice-ai-infrastructure.md>), [voice-ai-startup-funding](<https://devfeed.tech/tags/voice-ai-startup-funding.md>)

### AI overview

Gradium announced an extension of its seed funding to $100 million, with NVIDIA among the new investors, and plans to establish a San Francisco Bay Area office. The company says the funding will support AI research, product development, international expansion, and its office. Its products include real-time speech-to-text, text-to-speech, speech translation, on-device speech generation, and an open-source framework for building voice agents.

### Source excerpt

Gradium extends its seed funding to $100 million, welcoming new investors including NVIDIA, and opens a San Francisco Bay Area office to scale its real-time voice AI.

## Build a Real-Time Voice Interview Coach with TypeScript and LiveKit

DevFeed: [Build a Real-Time Voice Interview Coach with TypeScript and LiveKit](<https://devfeed.tech/articles/build-a-real-time-voice-interview-coach-with-typescript-and-livekit-21841.md>)

Original publisher: [Read original article](<https://www.thepolyglotdeveloper.com/blog/2026/05/build-a-real-time-voice-interview-coach-with-typescript-and-livekit/>)

Author: Nic Raboy

Published: 2026-05-06T22:00:00Z

Content type: tutorial

Language: en

Sources: [Nic Raboy](<https://devfeed.tech/sources/nic-raboy.md>)

Topics: [livekit](<https://devfeed.tech/topics/livekit.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [Frontend & real-time](<https://devfeed.tech/topics/frontend-real-time.md>), [Chat Bot](<https://devfeed.tech/topics/chatbot.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [apache](<https://devfeed.tech/tags/apache.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [build](<https://devfeed.tech/tags/build.md>), [coaching](<https://devfeed.tech/tags/coaching.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [interview](<https://devfeed.tech/tags/interview.md>), [job](<https://devfeed.tech/tags/job.md>), [livekit](<https://devfeed.tech/tags/livekit.md>), [llm](<https://devfeed.tech/tags/llm.md>), [other](<https://devfeed.tech/tags/other.md>), [project](<https://devfeed.tech/tags/project.md>), [questions](<https://devfeed.tech/tags/questions.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [resume](<https://devfeed.tech/tags/resume.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [voice](<https://devfeed.tech/tags/voice.md>)

### AI overview

The tutorial outlines a TypeScript interview coach that uses LiveKit to orchestrate a voice-based AI agent and frontend, with a web service managing uploads and application memory. Users can provide a job description and resume for role-specific interview questions and feedback on their answers and presentation. The stated setup uses Node.js 24; a LiveKit account is required, and its free tier should suffice at the project's scale. Apache Tika is optional: it can extract text from PDFs and other document formats, while Markdown is the fallback. The excerpt identifies the main components but does not include implementation steps.

### Source excerpt

Do you struggle with interviews? You're not alone! You can have the best interview notes in the world, but when you start having that vocal conversation, you might end up a deer in the headlights, fre... The post Build a Real-Time Voice Interview Coach with TypeScript and LiveKit appeared first on The Polyglot Developer.

## Gradbot: An open-source Rust framework for prototyping voice agents

DevFeed: [Gradbot: An open-source Rust framework for prototyping voice agents](<https://devfeed.tech/articles/gradbot-vibe-code-voice-agents-in-50-lines-of-code-81222.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/gradbot>)

Author: Gradium

Published: 2026-04-15T00:00:00Z

Content type: article

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [Jule](<https://devfeed.tech/topics/jule.md>)

Tags: [engineering](<https://devfeed.tech/tags/engineering.md>), [gradbot](<https://devfeed.tech/tags/gradbot.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-voice-ai](<https://devfeed.tech/tags/open-source-voice-ai.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [rust](<https://devfeed.tech/tags/rust.md>), [rust-voice-orchestration](<https://devfeed.tech/tags/rust-voice-orchestration.md>), [turn-taking-voice-agent](<https://devfeed.tech/tags/turn-taking-voice-agent.md>), [voice-agent-framework](<https://devfeed.tech/tags/voice-agent-framework.md>), [voice-agent-prototyping](<https://devfeed.tech/tags/voice-agent-prototyping.md>)

### AI overview

Gradbot is an open-source framework for prototyping voice agents. Its Rust core coordinates speech recognition, language model inference, and speech synthesis, with turn-taking, interruption handling, silence management, and asynchronous tool-call tracking. The article positions it for experimentation and recommends other orchestrators for production use.

### Source excerpt

Gradbot is our open-source framework for prototyping voice agents in minutes. Built on a Rust orchestration core, it handles turn-taking, interruptions, silence, and async tool calls so you can ship a working voice experience in around 50 lines of code.

## Time to First Audio: Measuring and Reducing TTS Latency in Voice Agents

DevFeed: [Time to First Audio: Measuring and Reducing TTS Latency in Voice Agents](<https://devfeed.tech/articles/time-to-first-audio-measuring-and-reducing-tts-latency-in-voice-agents-81245.md>)

Original publisher: [Read original article](<https://gradium.ai/blog/time-to-first-audio>)

Author: Gradium

Published: 2026-03-24T00:00:00Z

Content type: tutorial

Language: en

Sources: [Gradium](<https://devfeed.tech/sources/gradium.md>)

Topics: [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [livekit](<https://devfeed.tech/topics/livekit.md>), [WebRTC](<https://devfeed.tech/topics/webrtc.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency-voice-agent](<https://devfeed.tech/tags/low-latency-voice-agent.md>), [real-time-tts-streaming](<https://devfeed.tech/tags/real-time-tts-streaming.md>), [time-to-first-audio](<https://devfeed.tech/tags/time-to-first-audio.md>), [ttfa](<https://devfeed.tech/tags/ttfa.md>), [tts](<https://devfeed.tech/tags/tts.md>), [tts-benchmarking](<https://devfeed.tech/tags/tts-benchmarking.md>), [tts-latency](<https://devfeed.tech/tags/tts-latency.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-agent-latency](<https://devfeed.tech/tags/voice-agent-latency.md>), [voice-agents](<https://devfeed.tech/tags/voice-agents.md>)

### AI overview

The article explains how to measure time to first audio in streaming text-to-speech, including how to distinguish audio samples from container metadata and how to control variables in provider benchmarks. It also describes ways to reduce end-to-end voice agent latency through colocating components, streaming language model output into TTS, and reusing WebSocket connections. Its provider benchmark favors Gradium, and the article presents deployment options for its TTS service.

### Source excerpt

In natural conversation, the gap between one person finishing a sentence and the other starting to respond averages around 200 milliseconds. For voice agents this is the target to match.