Archive.
Posts originally published elsewhere, collected here with their canonical source.
108 posts
2026
Simba 3.0 now supports cloned and personal voicessimba-3.0 accepts cloned and personal voice_id values self-serve on POST /v1/audio/speech and /v1/audio/stream, the same way simba-english does; simba-3.2 cloningText-to-Speechvia speechify.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.TypeScriptvia speechify.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.Voice Agentsvia speechify.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.Text-to-Speechvia speechify.ai
Cloned voices can now run on Simba 3.2 with Speechify approvalPersonal cloned voices now synthesize on Simba 3.2, gated on manual voice cloning approval - once approved, pass the clone as voice_id with the model.Text-to-Speechvia speechify.ai
List available TTS models at runtime with GET /v1/audio/modelsCall GET /v1/audio/models to list the models you can pass to the TTS API, each with default and recommended flags and the languages it supports.Text-to-Speechvia speechify.ai
Simba 3.2 is live on the TTS API as the recommended English modelSimba 3.2 is live on the Speechify TTS API: streaming-native, with lower time-to-first-byte, richer expressivity, and a curated voice allow-list.Text-to-Speechvia speechify.ai
WE'RE NUMBER ONESimba 3.2 is #1 on the Artificial Analysis TTS leaderboard and the top-rated real-time voice on Voice Arena's blind, listener-voted board - at the lowest price.Comparisonvia speechify.ai
Building an automated audiobook pipeline with the Speechify TTS APIAn automated audiobook pipeline in Python: chunk long text on sentence boundaries, synthesize each chunk with the TTS API, then stitch the MP3s with ffmpeg.Text-to-Speechvia speechify.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.Pricingvia speechify.ai