Neuphonic
A text-to-speech provider with a cloud streaming API and open NeuTTS models that run on CPU, on-device or on-premise.
About Neuphonic
Teams that need speech output on private infrastructure or offline devices cannot send every request to a cloud GPU service.
Who it’s for
- Developers who need text-to-speech that runs locally on CPUs or edge devices
- Teams adding streaming speech to voice agents through LiveKit, Pipecat or Twilio
When to consider it
Consider Neuphonic when you want the option to run speech generation on your own hardware without a GPU, and a hosted streaming API when you do not.
Tradeoffs & limitations
- Commercial terms vary by model: NeuDecide and NeuCodec use Apache 2.0, while NeuTTS-2E uses the NeuTTS Open License with commercial-use conditions.
- On-device and on-prem deployments are arranged by contacting the company; the cloud API requires an internet connection.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Neuphonic.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Nov 1, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Neuphonic official website
A text-to-speech provider with a cloud streaming API and open NeuTTS models that run on CPU, on-device or on-premise.
Based on official pages and announcements checked on 2026-11-01. No hands-on test, performance benchmark or popularity ranking is claimed.