# How Speechify uses Baseten

**44%**: “Speechify's cost per million characters dropped by 44%”

As published on [baseten.co](https://www.baseten.co/resources/customers/speechify-real-time-text-to-speech/), May 2026. Captured by usedby on 2026-10-09.

- Company: [Speechify](https://www.usedby.ai/companies/speechify.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)
- Teams: Engineering, Platform Engineering, AI Platform, Research

## What the story says

Speechify runs its SIMBA text-to-speech models, plus text normalization, voice conversion, sound FX and page parsing models, on Baseten for real-time, high-volume inference. Researchers deploy models themselves with Truss, and traffic-based autoscaling replaced a self-managed GPU stack.

Summary written by usedby from the source page, in English. The figures are those of Baseten and Speechify, not ours.

> Because of Baseten's efficient autoscaling, model performance and infrastructure optimizations, Speechify's cost per million characters dropped by 44%, as traffic on its platform grew 7% during the same period.

- **30–50%**: “Across the SIMBA TTS family, p99 inference latency dropped 30–50% post-migration”
- **4.5x**: “Replica startup became 4.5x faster”
- **50-70%**: “latency spikes dropped by 50-70%”
- **76 ms**: “Its new SIMBA 3.0 vLLM models run on Baseten with 76 ms p50 TTFB.”

> A researcher shipped SIMBA 3.0 vLLM into production by themselves. That would have taken days of work from our entire AI Platform team with our old infrastructure stack.
>
> Kai Krause, VP of Engineering and AI

Source: [baseten.co](https://www.baseten.co/resources/customers/speechify-real-time-text-to-speech/), captured 2026-10-09.

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure 44% is printed word for word on the page, near the name of Speechify.
- Checked: the passage quoted above is copied word for word from the page, near the name of Speechify.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Speechify uses Baseten. Confirmed line. Latest check across sources: 2026-10-09.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/speechify-baseten · How we check: https://www.usedby.ai/methodology