AssemblyAI-TTS-1: low-latency text-to-speech built for live voice agents
AssemblyAI's first text-to-speech model, generally available 29 Oct: 4,000+ voices, instant cloning from short samples, six languages, streaming over HTTP, WebSocket and OpenAI-compatible APIs, priced at $15 per million characters.
Why it matters
Completes AssemblyAI's voice-agent stack (streaming speech recognition plus an LLM gateway plus speech synthesis) on one API key, aimed at live phone agents where latency and clean interruption handling decide whether a call feels real.
What you could build with it
A small clinic could build a phone agent that books appointments and reads back confirmations in a cloned receptionist voice, interrupting cleanly when the caller talks over it.
Does it hold up?
Usable now as a paid streaming API with interruption support, but latency and voice-quality claims are vendor-reported so far; independent production call data is not yet public.
Built with AssemblyAI-TTS-1
- AssemblyAI launches new text-to-speech API modelnews · Launch report: TTS-1, 4,000+ voices, instant cloning, six languages, $15 per million characters.
- AssemblyAI adds speech generation for voice agents at $15 per million charactersnews · Launch analysis noting the move from transcription into speech generation and that production performance at scale remains unproven.
- AssemblyAI details Python voice agent build with tool callingblog · Tutorial combining streaming speech recognition, LLM Gateway tool calling and TTS-1 into a real-time voice agent that can be interrupted.
Learn more
First spotted on article: source.
More AI models
Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72NVIDIA Cosmos 3.5 world models: now openly availableNVIDIA's Cosmos 3.5 family of open world foundation models for robots, autonomous vehicles and vision agents is now…models · JEV 0.71NVIDIA RFD4-Proteina: open protein-design BioNeMo modelOpen protein-design model from NVIDIA and the Baker Lab at UW Medicine's Institute for Protein Design, announced at…models · JEV 0.7
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.