AssemblyAI text to speech: coming soon, and what Sume has today
AssemblyAI's product menu lists a Text-to-Speech API as coming soon. Sume TTS is available now: what a call takes, the 20000-character cap, and word timings.
AssemblyAI's product menu, read 2026-10-01, shows "Text-to-Speech API" with a "coming soon" label beside the Voice Agent API and Dictation API. Sume TTS is a live endpoint today: POST /v1/tts-1.0/generate, which takes a transcript and returns audio.
This post says nothing about AssemblyAI's unreleased product beyond that label.
What does the AssemblyAI page say?
Only that a Text-to-Speech API is coming soon. No pricing, voices or dates appear in the snapshot, so there is nothing to compare.
What does a Sume TTS call take?
The schema calls it the Sume TTS 1.0 text-to-speech request. Send a transcript (maximum 20000 characters) and pick a voice with avatar_id / avatar_handle or voice.id. Optional timestamps.words and segmentation.mode=sentence return word timings.
| Route | Use |
|---|---|
POST /v1/tts-1.0/generate | Sume TTS 1.0 |
POST /v1/tts-router/generate | A named engine from the Router catalog |
GET /v1/tts-router/models | List Router models |
When would I use the Router route?
The Router request requires a TTS Router catalog model id, so you name the engine. Use TTS 1.0 when you do not care which engine runs.
What do I do with the audio afterwards?
Word timings feed captions or cut lists, and for join and slice work see mp3 or wav. The overview is in text to speech API.
Sources
Related posts
More in Models
- AssemblyAI Universal-3.6 Pro 32 languages vs Sume STT language_code
AssemblyAI streaming defaults to Universal-3.6 Pro with 32 languages; 3.5 Pro has 19. Sume STT 1.0 takes one optional language_code hint and auto-detects.
- Cartesia Sonic 2 and Turbo stop October 20: Sume model ids
Cartesia retires sonic-2 and sonic-turbo on October 20, 2026. Sume's TTS Router lists sonic-3.6, 3.5, 3, latest and preview; here is what to send instead.
- Sonic 3.6 written disfluencies: pacing and Sume's emotion guide
Sonic 3.6 shifts pacing for written hesitations like uh. How to write a natural-sounding transcript, and what Sume's optional emotion guide adds.
- Cartesia STT keyterms for brand names, and Sume STT without keyterms
Cartesia STT adds keyterm prompting for brand names and invented words. Sume STT has no keyterm field, so here is how to fix brand names after transcription.
Written by Sume