Luke Oliff · Blog
Writing.
Everything I've published, in one place. Posts live at the root of this site, not under a /blog prefix, so links stay short.
SearchAI (4)API (3)Askdev (1)Beginners (1)Blacklivesmatter (1)Career (3)CEO Pay (1)Community (1)Contributorswanted (1)Culture (1)Deepmind (1)Developer Relations (24)Devrel (1)Discuss (2)Disinformation (1)Express (1)FTSE100 (1)Git (2)Github (1)Go (1)Google (1)GPG (1)Hacktoberfest (1)Help (1)Inclusion (1)JavaScript (18)Jwt (1)Lambda (1)Mentalhealth (2)Meta (1)Mongodb (1)Netlify (2)News (1)Nexmo (1)Node (3)Node.Js (1)Nuxt (3)Open letter (2)Opensource (4)Passport (1)Pay Transparency (1)Politics (1)Programming (1)Security (8)Series (1)Showdev (8)Software Security (1)Text To Speech (3)Text-to-Speech (36)Typeform (1)United Kingdom (1)Voice AI (42)Vue (1)Webdev (1)Wecoded (3)Womenintech (3)Workfromhome (2)
2026
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
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
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
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
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
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
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