AssemblyAI

@AssemblyAI

Access powerful AI models to transcribe and understand speech via a simple API. Try our no-code playground for free 👉 assemblyai.com/playground

assemblyai.com

Joined October 2017

415 Following

45.9K Followers

4 Affiliates

Replies Reposts Media

AssemblyAI
@AssemblyAI
Oct 29
Free ice cream in SoMa 🎃🍦 Yesterday we launched TTS-1, our Text-to-Speech model built for voice agents. To celebrate, the AssemblyAI ice cream truck is back with customer flavors on the menu: 🍦 Granilla ft. @meetgranola 🍪 Cookies & Commure ft. @CommureOS 🥜 Retell in a
AssemblyAI
@AssemblyAI
Oct 28
We are live on OpenRouter as well!!
OpenRouter
@OpenRouter
Oct 28
AssemblyAI-TTS-1 is now live on OpenRouter! @AssemblyAI's first text-to-speech model, built for voice agents. Ranked in the best quadrant for speed and accuracy, and highest naturalness for models at $15/1M characters or less, per @cekuraAi's benchmark. 4,000+ voices, served
Quote
AssemblyAI
@AssemblyAI
Oct 28
Introducing AssemblyAI-TTS-1, our first text-to-speech model. Natural speech for voice agents, streaming in 90 ms, at $15 per million characters. On accuracy, naturalness, and cost together, it’s the best TTS model you can run at scale.
1
AssemblyAI
@AssemblyAI
Oct 28
Tips our team found for accurate voice clones: - WAV, not MP3 - 15 to 25 seconds of reference audio - Scripted or unscripted: try both - Pick the mic that fits your use case Voice cloning docs: assemblyai.com/docs/tts/clone…
AssemblyAI
@AssemblyAI
Oct 28
Artificial Analysis evaluated AssemblyAI-TTS-1 in its arenas: • 162 characters/sec, faster than Sonic 3.6 • Top 10 in Controlled Voice, same 8 cloned voices across models • Top 12 in Provider Voice • Of the 11 models ranked above it, 9 cost more than $15/1M characters
Artificial Analysis
@ArtificialAnlys
Oct 28
AssemblyAI has launched its first Text to Speech model! AssemblyAI-TTS-1 enters the top 12 in our Provider Voice Arena and the top 10 in Controlled Voice @AssemblyAI has launched its first Text to Speech model, AssemblyAI-TTS-1! We evaluated its performance across both Speech
4
AssemblyAI
@AssemblyAI
Oct 28
Independent results from Cekura's text-to-speech benchmark, 27 models tested: • #1 on phone numbers and codes (91.7%) • Best quadrant for speed and accuracy • 4.50 naturalness, highest of any model at $15/1M characters or less • Every medical term read correctly