Luke Oliff · Author
Posts by Luke Oliff
Best TTS Providers 2026: Comparison of the Top 10 APIsThe top 10 text-to-speech APIs of 2026, benchmarked on the independent Artificial Analysis Speech Arena. Simba 3.2 is tied for the best-rated voice at $6 to $10 per million characters, a fraction of Cartesia, Deepgram, and ElevenLabs. Self-hosted models left out.Voice AI
Open Weights Are Eating AI: Here Are the 7 Best Open TTS Models and the Gap Nobody MentionsThis is the biggest open-weight week AI has ever had: DeepSeek V4’s stable release lands July 24 and Moonshot’s Kimi K3 weights go free on July 27, days after K3 topped a major coding leaderboard…Voice AI
Fortnite Is About to Run the Biggest Real-Time TTS Deployment in GamingEpic Games is giving 36 Fortnite characters AI voices for a “conversations” feature that leaves its experimental phase on July 30, 2026, letting creators publish islands where NPCs talk back,…Voice AI
Simba 3.0 now speaks six European languages; Simba 1.6 marked legacySimba 3.0 is no longer English-only — it now officially covers English plus German, Spanish (ES/MX), French, Italian, and Brazilian Portuguese. The same release flags the Simba 1.6 models as legacy and confirms Simba 3.0 accepts cloned voices.Voice AI
Five Voice AI Stories from Mid-July 2026 That Actually MatterMid-July 2026 gave voice AI a new leaderboard king, a 70% price cut from Google, a $22 billion valuation rumour, a nine-figure seed round, and an AI Gene Wilder. Here are the five stories worth your…Voice AI
Qwen-Audio-3.0-TTS Plus Review: What Taking #1 Actually Bought AlibabaAlibaba’s Qwen-Audio-3.0-TTS-Plus is the new #1 on the Artificial Analysis Speech Arena leaderboard, with an Elo of 1,236 (±17) from 1,305 blind listener votes. That puts it two points ahead of…Voice AI
Set a per-agent maximum call durationVoice agents now carry a max_call_duration_seconds field — a hard per-agent wall-clock cap on a single call. When a call reaches it, the agent ends automatically; null keeps the previous behavior of bounding calls only by your plan's ceiling.Voice AI
The Rules for Synthetic Voices Arrived This Month from Three Different Directions at OnceIn the space of about a week, synthetic voices got rule-making at three separate layers of the stack. TikTok Shop banned AI-generated voices from live commerce streams on July 15, with violations…Voice AI
Filter GET /v1/voices by type, locale, gender, and modelGET /v1/voices now accepts type, locale, gender, and model query filters, applied before pagination so pages stay full — so you can fetch, say, only English cloned voices that support Simba 3.2 in a single call.Voice AI
Per-plan API rate and concurrency limits are now publishedThe API limits reference now lists per-plan rate limits (requests per second, plus an Agents burst) and concurrency limits for both the TTS and Agents surfaces, and 429 responses carry a docs_url plus distinct rate_limited and concurrency_limited error codes.Voice AI
Brussels Just Handed Every Voice Assistant the Thing Google Would Never SellOn July 16, 2026, the European Commission adopted binding Digital Markets Act decisions ordering Google to open Android to rival AI assistants, granting certified third-party assistants voice…Voice AI
AMD Just Put Text-to-Speech in the Local AI Stack by DefaultAMD released Lemonade 11.0 on July 15, 2026, and the headline feature is text-to-speech: an OpenMOSS backend with voice-cloning and voice-design models, plus a dedicated TTS panel in the UI.…Voice AI
Building an AI Voice Cloning Web App with Next.js and SpeechifyClone a voice from a browser upload, synthesize speech with it, and keep your API key server-side. A working Next.js voice cloning app built on the Speechify API, no GPU required.Voice AI
Listeners Just Voted and the AI Voices Won. Nobody Told Them They Were Voting.Two studies published in mid-July 2026 found that ordinary listeners can’t reliably tell AI voices from human ones, and in some settings actively prefer the synthetic option. Edison Research, in a…Voice AI
Streaming TTS directly to the browser with Web Audio APIStream Speechify TTS as raw PCM, keep the API key server-side, and schedule each chunk into the browser's Web Audio API for low-latency playback.Voice AI
Add a better voice to Deepgram's Voice Agent with SpeechifyPoint Deepgram Voice Agent at the open-source tts-shims OpenAI-compatible proxy to speak with a Speechify voice. The shim answers Deepgram's open_ai TTS request and keeps your Speechify key server-side.Voice AI
Controlling Emotion and Timing in TTS with SSMLUse SSML emotion tags, pauses, prosody, emphasis, and pronunciation aliases to shape Speechify TTS output from one API request.Voice AI
Voice AI Is Worth Billions and Speech Is Nearly Free. Both Are True.In the first two weeks of July 2026, ElevenLabs opened talks for a tender offer at a roughly $22 billion valuation, Paris-based Gradium closed a $100 million seed round backed by Nvidia, and…Voice AI
Gene Wilder's Voice Is Back and the Interesting Part Is the PaperworkNetflix is using an AI recreation of Gene Wilder’s voice in “Wonka’s The Golden Ticket,” a nine-episode reality competition [premiering September 23,…Voice AI
Cloned voices can now run on Simba 3.2 with Speechify approvalPersonal cloned voices can now be synthesized on the curated Simba 3.2 model. Given the model's quality bar, each clone is gated on manual Speechify approval of the voice key, while simba-english and simba-multilingual keep serving clones self-serve.Voice AI
List available TTS models at runtime with GET /v1/audio/modelsA new GET /v1/audio/models endpoint returns the models you can pass as the model parameter, each with a default and recommended flag plus the languages it supports — so a model picker can be built at runtime instead of hardcoding the list.Voice AI
OpenAI Shipped Its Best Voice Model Where Developers Can't Touch ItOpenAI released GPT-Live-1 and GPT-Live-1 mini on July 8, 2026, a pair of full-duplex conversational models that replace Advanced Voice Mode in ChatGPT. They can listen and speak at the same time,…Voice AI
Simba 3.2 is live on the TTS API as the recommended English modelSimba 3.2 is now available on POST /v1/audio/speech and /v1/audio/stream — a streaming-native Simba 3 model with lower TTFB, richer expressivity, and a curated voice allow-list, recommended for new English integrations.Voice AI
WE'RE NUMBER ONESimba 3.2 is #1 on Artificial Analysis, the independent TTS benchmark. On Voice Arena's blind, listener-voted board it's the #1 real-time voice and #1 on price — the model above it isn't real-time, the nearest at its quality costs 7x more. Nothing you can ship beats it.Voice AI
Building an automated audiobook pipeline with the Speechify TTS APITurn long-form ePub or Markdown into a single narrated chapter MP3 with a runnable Python demo: chunk on sentence boundaries, synthesize each chunk, stitch with ffmpeg.Voice AI
API keys can now enforce monthly USD spend limitsSpeechify API keys can now carry a monthly USD spend limit, returning 402 spend_cap_exceeded once a key reaches its budget for the calendar month.Voice AI
Switch to Speechify from inside speech-sdkSpeechify is now a direct provider in speech-sdk. Switch existing calls over with a factory function and an API key, no new client required.Voice AI
TTS now accepts sample-rate and bitrate-specific output formatsSpeechify TTS speech and streaming endpoints now accept output_format values like pcm_16000, ulaw_8000, and bitrate-tuned mp3 variants without changing existing callers.Voice AI
The API now exposes more safety limits at the edgeSpeechify added rate-budget response headers, global JSON body-size handling, clearer 413 and 415 errors, and pre-auth IP throttling for token-mint paths.Voice AI
Dynamic video narration using the Speechify Voice Cloning APIClone a voice from a short sample and use it to narrate dynamic video content programmatically via the REST API.Voice AI
Your pay hasn't moved since 2008. FTSE 100 CEO pay just set its fourth record in a row.Your pay hasn't moved since 2008. FTSE 100 CEO pay just set its fourth record in a row.Pay Transparency
Google just cut the price of decent speech by 70%, quietlyGoogle just cut the price of decent speech by 70%, quietlyAI
Inworld TTS-2, six weeks after the price cut: the consumer-app play, reviewedInworld TTS-2, six weeks after the price cut: the consumer-app play, reviewedAI
Qwen-Audio-3.0-TTS Flash: Alibaba just came for the real-time marketQwen-Audio-3.0-TTS Flash: Alibaba just came for the real-time marketAI
Workspace webhooks now have endpoint management and versioned payloadsSpeechify workspace webhooks now support managed endpoints, delivery history, a resource.action event catalog, combined signatures, and per-endpoint API versions.Voice AI
API keys now carry clearer scopes and usage attributionSpeechify API keys now have cleaner scope tiers, service-account inheritance, and usage attribution that makes spend easier to trace back to a workload.Voice AI
How we think about latency in SpeechifyAI voice agentsBaseten published a case study on the SpeechifyAI voice agent stack. This is our view on why model co-location matters for live calls.Voice AI
Service accounts are now machine identities for the Speechify APIService accounts give Speechify API workloads their own identity, scope ceiling, key rotation flow, usage attribution, and short-lived child keys for agent sessions.Voice AI
Building real-time captions with Speechify TTS speech marksUse the Speechify API's word-level timestamps to generate accurate WebVTT captions for your synthesized audio.Voice AI
Build and Agents API fields moved toward one naming shapeBuild and Agents received a small API naming cleanup on June 28, including not_specified voice gender and several Agents field-name migrations.Voice AI
Streaming TTS in Python with SpeechifyHow to stream audio from the Speechify TTS API in Python using the SDK and native requests. Covers chunked streaming to disk and piping audio to a player without waiting for the full payload.Voice AI
GET /v1/voices now returns a pagination-ready envelopeThe Build API moved GET /v1/voices from a bare array to a voices object with pagination fields, making the response shape safer for SDKs and future growth.Voice AI
Idempotency-Key is now wired across side-effect API callsSpeechify now supports Idempotency-Key on the API calls most likely to be retried, including calls, batches, purchases, spend paths, and service-account key minting.Voice AI
Speechify-Version gives API clients a stable date pinSpeechify APIs now support the Speechify-Version header, so HTTP clients can pin a dated contract while SDKs send their build-date version automatically.Voice AI
Using TTS in Node.js with SpeechifyA practical guide to synthesizing speech in Node.js using the Speechify TTS API. Covers installation, a basic synthesis call, streaming audio to disk, and what to reach for next.Voice AI
TTS stream responses are documented as raw audio streamsThe Build docs now spell out that POST /v1/audio/stream returns chunked raw audio, not JSON, with clearer response content types and codec notes.Voice AI
Agents now expose live operations APIs for analytics and interventionSpeechify Agents added live transcript streaming, take-over actions, per-action RBAC, analytics queries, and saved dashboard APIs for monitoring live voice operations.Voice AI
Launching the Speechify CookbookA small, public repo of runnable Speechify recipes. Pick a folder, drop in your API key, run it. TypeScript and Python today, SDK and native REST side by side.Voice AI
Hello Speechify DevelopersWelcome to the new Speechify developer blog. Expect updates from the AI and labs teams, product news, collaborations, and technical guides for the Speechify TTS API.Voice AI
Best Text-to-Speech API: Top Voice Quality at the Lowest Price (2026) | SpeechifySpeechify SIMBA 3.0 ranks #7 globally on Artificial Analysis — above ElevenLabs, Google, and OpenAI — from $6 per million characters. Compare top TTS APIs.Voice AI
A Rising Tide Lifts All BoatsI used AI to help edit this article. The experiences, the arguments, the disappointments, and frustrations are mine. Every example is real. But I am, despite being British, not great at written…
Voice Agents API is now public betaSpeechify Voice Agents is now publicly documented, with guides and API reference pages for agents, conversations, tools, knowledge bases, calls, and monitoring.Voice AI
I'm not apologising for being productiveBy the time a child with ADHD reaches the age of ten, they've received an estimated 20,000 more corrective or negative messages than their neurotypical peers. Not a little more. Twenty. Thousand.…
The inequity of contributing guidesYour CONTRIBUTING.md isn't welcoming. It's a gatekeeping document.Most open source projects have a contribution guide.
Slack is your remote team's social media. Treat it like it.I've worked remotely for years. Nine of them, full time - four and a half at Deepgram. No office, no watercooler, no accidentally bumping into someone in the kitchen and finding out they're also…
We Built a Self-Service Support Bot That Customers Install ThemselvesHow Deepgram built a self-service AI support bot for Slack — customers install it, link their project, and get answers from docs instantlyVoice AI
An open letter on AIAI is a tool — a hammer. It's not good or bad; it's about how we use it. On creativity, programming, and staying human through the next industrial revolution.Open letter
An open letter on politicsWhy I judge people by their politics — and why staying neutral is a choice too. On democracy, media manipulation, and raising two kids in the world we're building.Open letter
Time to Leave? Time to Rebuild! Making Twitter2.0Time to Rebuild! When Elon Musk announced his intention to purchase Twitter in April 2022, he did so with grand promises. Tagged with go, programming, series.Go
The End of X (Or, It Should Be): How Elon Killed TwitterWhen Elon Musk announced his intention to purchase Twitter in April 2022, he did so with grand promises. Tagged with news, disinformation, security.News
Just Surviving: Working Remotely for BeginnersFollowing on from my last post where I talked about how difficult working remotely can be, today I am posting some of my advice on how to maintain a positive you-work relationship, and healthy work-life balance. Tagged with workfromhome, mentalhealth.Workfromhome
I Love Working Remotely, Even Though It Sucks at TimesI love and hate remote work. It drains my social battery, needing human interaction to recharge. The shift to home offices during the pandemic led to lost connections and innovation. Tagged with workfromhome, mentalhealth.Workfromhome
A Guide to Respectful API Back-Off StrategiesThis guide provides a general framework for handling Deepgram's 429 response errors through effective back-off strategies. Depending on the specifics of your application and usage patterns, you may need to adjust these strategies to fit your needs. Always refer to the latest Deepgram documentation for up-to-date information on their API and rate limits.Voice AI
Auto-Playback Across Devices (especially iOS)Auto-Playback Across Devices (especially iOS)Voice AI
Upgraded - The Deepgram JavaScript SDK v3Upgraded - The Deepgram Javascript SDK v3.Voice AI
Luke Oliff Joins the Developer Relations Team - Deepgram Blog ⚡️Luke Oliff joins the Developer Relations team at Deepgram!Voice AI
Introducing Deepgram Starter Apps - Deepgram Blog ⚡️Deepgram's Starter apps provide all users with a seamless and efficient onboarding experience.Voice AI
I'm Luke and I pledge to help close the gender gap in 2022!Much like last year, I intend to give my space to those women who inspired me in the last... Tagged with wecoded, career, womenintech.Wecoded
5 Ways to Build a Node.js API5 ways to build lightweight Node.js APIs, using popular frameworks or Node's standard libraries.Developer Relations
I'm Luke, and I support women in tech.Last year I wrote about things I advocated that we can all do to further equality in tech. I still... Tagged with wecoded, career, womenintech.Wecoded
Server-Side Analytics with Jamstack SitesJamstack sites don't have a backend. That makes their ability to gather analytics particularly vulnerable to ad-blockers. Let's fix that problem.Developer Relations
Migration From WordPress to JamstackThe Great Migration: Months of planning, tons of research, 3 proof of concepts. This is the result.Developer Relations
Get Your Twitch Stream Live on Your WebsiteBuilding a small Netlify function to determine whether a Twitch stream is live or not. Tagged with netlify, lambda, javascript, showdev.Netlify
The Perfect Breadcrumbs (in Nuxt)A small component for semantic breadcrumbs in Nuxt (or VueJS). Tagged with nuxt, javascript, showdev.Nuxt
Speed up Nuxt Builds on NetlifyIf you're not careful, your build times for Nuxt can spiral out of control. This is my journey to get from 30 minutes to 1 minute builds. Tagged with netlify, nuxt, showdev, javascript.Netlify
Hacktoberfest - Open Source and Lots MoreI love Hacktoberfest. The very idea of it is to promote folks discovering the process of open-source... Tagged with hacktoberfest, opensource, contributorswanted.Hacktoberfest
Other Ways to Contribute to Open Source This HacktoberfestNot a programmer? There are other ways to contribute to open source. From translating docs to removing uninclusive or patronising language.Developer Relations
Change Git's Default Branch From MasterBecause actually whatever your argument against it, you're probably wrong. Tagged with blacklivesmatter, git, showdev.Blacklivesmatter
Guy's Bot - Inclusive Language in SlackWorking remake of popular Slack Bot guys-bot-for-slack with modern Slack APIs, using a basic implementation of Slack's Node.js SDKs. Tagged with showdev, node, inclusion, opensource.Showdev
Any TILs from your package managers library recently?Any TILs from your package managers library recently?. Tagged with discuss, opensource.Opensource
The Ultimate `npm run dev`Automatically reloading node application accessible with a public URL. The ultimate npm run dev. Tagged with showdev, node, javascript, opensource.Javascript
Export WordPress Posts to NuxtA simple CLI to suck your WordPress posts down into. Tagged with nuxt, javascript, webdev, showdev.Nuxt
Building a Slack Clone Using Vue Part 1Ever wanted to create a chat application like Slack? Learn to build a clone of Slack, using Vue.js and the Vonage Conversation API.Developer Relations
Does Changing a Username or Organisation Name Provide Redirects?Does Changing a Username or Organisation Name in Dev.to Provide Redirects?. Tagged with askdev, help, meta.Askdev
Using Tailwind CSS with Vue.jsSetting up Vue.js to use the Tailwind CSS framework. Tagged with vue, javascript, beginners.Vue
In Celebration of International Women’s Day 2020We are proud to be elevating voices within the Vonage community this International Women's Day.Developer Relations
I'm Luke, and I Could Do MoreWhen I started at Vonage (née Nexmo) as an Advocate, I was pretty new to Developer Relations. I disco... Tagged with wecoded, womenintech, career.Wecoded
Chat Pagination with Infinite ScrollingLearn how to add Infinite Scrolling to a message UI using JavaScript to support paginated messages from the Vonage Conversation Client SDK.Developer Relations
Create a Simple Messaging UI with BootstrapThe design-web is awash with all sorts of examples of messaging UIs, but developers lack choice on frameworks. You can use basic Bootstrap components to create a simple messaging UI.Developer Relations
The Ultimate DevRel Guide To TravelDiscover the ultimate travel tips and hacks, to make your travel more fun and bearable, from an award-winning team that is always on the move.Developer Relations
Register to Chat with TypeformRegister to Chat with TypeformTypeform
Adding Voice Functionality to an Existing Chat ApplicationEnable audio communication between web users using our Client SDKDeveloper Relations
Snapchat Style Filters with Tracking.js and VonageAdd facial tracking using Tracking.js and create some cool OpenTok.js Snapchat style filters for a video stream. Be Batman or just freak some people outDeveloper Relations
Code Security — The Importance of Securing Your Version ControlCode Security — The Importance of Securing Your Version ControlGit
How to Manage a Collection of Secure API Endpoints with PostmanLearn how to use Postman - an API development environment - to manage collection of public and secure API endpoints and streamline the de...Security
Auth0 Adds Discourse Forum into Blog for Comments EngineAuth0 is integrating Discourse into our custom JAMstack static blog, as the comment engine. This will better serve readers with queries a...Security
Hackference 2018 RecapHackference is a three-day conference and hackathon for attendees to learn something new. Auth0 sponsored this year, with Jeremy Meiss gi...Security
First Timers Guide to Contributing to an Open Source ProjectWhat is open source? How to contribute to an open source project? Check out the First Timers Guide, here - pay it forward by learning how...Security
Travel Industry APIs - Learn About This Industry's Digital TransformationThe Travel Industry is one of the world's fastest-growing sectors. Learn about the digital transformation taking place and how to acceler...Security
Common Threats in Web Application SecurityWe attempt to cover a comprehensive security strategy for web applications, to protect against common threats in web application security...Security
Elixir & Phoenix Tutorial: Build an Authenticated AppYou can't escape Phoenix if you're looking for a good framework to build on when using Elixir.Security