Archive.
Posts originally published elsewhere, collected here with their canonical source.
103 posts
2026
Widget bundle compression and session spend-limit 402The voice-agent widget is now served compressed - 676 kB down to 190 kB when it was measured - supports version-pinned URLs with subresource integrity, and session creation returns 402 when a spend limit or budget is hit rather than a 500.Widgetvia speechify.ai
TTS 404s now name the fix instead of a generic not-foundPOST /v1/audio/speech, /stream, and /stream/with-timestamps now return voice_not_found or a model-not-found message on a missing voice or model, instead of an opaque passthrough 404.TTSvia speechify.ai
Speech generation in the Vercel AI SDK with SpeechifyThe AI SDK ships generateSpeech() but no Speechify provider. So we wrote one: a dependency-free custom speech model that maps POST /v1/audio/speech onto the SDK's SpeechModelV4 interface, key held server-side in a Next.js route.Next.jsvia speechify.ai
Free tier TTS requests get a burst allowanceFree-tier /v1/audio/* requests get a 10-request burst bucket instead of capping at the 1 req/s sustained rate, so a first quickstart script no longer 429s on its second call.APIvia speechify.ai
Every public API header now has one canonical, un-prefixed nameSpeechify-Request-Id and RateLimit-* are now the canonical header names across the public API; the old X-prefixed spellings keep working until 2027-07-24.APIvia speechify.ai
Voice agents can now switch language mid-callOne agent serves multiple languages in a single session, with no transfer and no dropped context - configure it with additional_languages.Agentsvia speechify.ai
Simba 3.2 is our recommended TTS model: what changed and how to migratesimba-3.2 is now the recommended Speechify TTS model, and GET /v1/audio/models lets you discover it at runtime instead of hardcoding a model list. What shipped, the voice allow-list, and how to move off simba-3.0.Changelogvia speechify.ai
Agent test runs get clear 402 errors on balance and plan tier checksAll four agent test-run endpoints now document 402 for a depleted balance or an exhausted spend limit, the single-run path finally takes the admission gate its siblings already had, and an explicit over-tier model override is refused instead of being honoured unchecked.Agentsvia speechify.ai
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 #1 on Artificial Analysis at $6 to $10 per million characters, above every ElevenLabs, Cartesia and Google model. Self-hosted models left out.TTSvia speechify.ai
Streaming TTS now carries word-level speech marksA new endpoint streams speech marks alongside audio, so captions and text highlighting no longer need the non-streamed API.TTSvia speechify.ai