AssemblyAI-TTS-1 hits 162 chars/sec, fastest among major TTS models at $15/1M characters
ArtificialAnlys · x · 2026-10-29
Artificial Analysis benchmarked AssemblyAI's first TTS model:
- Speed: 162 characters per second, beating Cartesia Sonic 3.5 (148.6), Mistral Voxtral 3 TTS (112.3), ElevenLabs Eleven v4 (75.1) and Gemini 3.8 Flash TTS (53.4).
- Price: $15/1M characters, cheaper than Gemini 3.8 Flash TTS ($16.5), Qwen-Audio-3.1-TTS-Plus ($19.3) and Eleven v4 Turbo ($40), though pricier than Speechify Simba 3.2 ($6.6).
Overall it lands in the "fast with mid-tier pricing" bucket; a customer-service sample clip was also released.
More from Multimodal
- Apple showcases ComfyUI on new M5 touchscreen MacBook Pro page — lostaccountby2fa · 2026-10-29
- tts-audiobook-tool uses an LLM to cast characters and generate full-cast audio dramas — llamabott · 2026-10-29
- SenseNova open-sources Code2Video, a 27B model that makes videos by writing code — quietsam8 · 2026-10-29
- Higgsfield wrapper drama: user rebuilds AI person-swap video workflow in 30 minutes — ravisparikh · 2026-10-29
- CapCut Halloween Sale: Pro Up to 60% Off, Dreamina for $0.29 — FellMentKE · 2026-10-29
- HeyGen launches Voice STS, transferring pauses and whispers to your avatar — HeyGen · 2026-10-29