---
title: "Self-hosted vs API speech-to-text: how to decide"
description: "When to run an open speech-to-text model yourself and when to pay a hosted API. Cost at your volume, latency, privacy, languages and features, side by side."
canonical: "https://www.fermionresearch.com/speech/self-hosted-vs-api-speech-to-text/"
source: "Fermion Research"
---

Speech recognition/facts checked 13 November 2026

# Self-hosted vs API speech-to-text: how to decide

An API is the fastest way to start and the easiest to scale down. Running an open model yourself wins on cost at steady volume and on keeping audio inside your environment. Most teams should decide on volume and data rules first.

[Self-host a speech-to-text server](https://www.fermionresearch.com/models/phonon-2-5/self-host/)

## The short answer

Self-host speech-to-text when you have steady volume or audio that must not leave your environment; use a hosted API when volume is small or spiky, or when you need features open models lack, such as speaker labels, 90+ languages or managed streaming at scale. At steady volume, a measured self-hosted open model cost $0.00204 per audio hour, against $0.012 to $0.96 for hosted list prices.

## Side by side

Self-hosted figures are Fermion Research measurements; API figures are list prices and features on the providers' own pages, read 2026-11-11 to 2026-11-13.

| Factor | Self-hosted open model | Hosted API |
| --- | --- | --- |
| Cost per audio hour | $0.00204 measured (Phonon-2, L4 GPU, 60 % utilisation) | $0.012 (hosted Whisper turbo) to $0.96 (Google Chirp 3), list prices |
| Fixed cost | servers whether busy or idle, plus engineering time | none; pay per use |
| Latency | no network round trip when on the same machine or network | upload time plus the provider's queue |
| Where audio goes | stays in your environment | sent to the provider; terms vary |
| English accuracy (Open ASR Leaderboard, seven sets) | best open row 4.29 % word error | best closed row 3.68 % word error |
| Languages | 25 (Phonon-2.5) to 99 (Whisper) | up to 90+ (ElevenLabs Scribe v2) |
| Features | transcription, word timestamps, hotwords on some models | often adds speaker labels, redaction, summaries |
| Scaling | you add machines | the provider scales |

## When a hosted API is the better choice

- Low or unpredictable volume: a few hundred hours a month costs little at any list price, and an idle server would cost more.
- You need speaker labels, redaction or summaries out of the box.
- You need languages outside the open models you can run, or the lowest possible English error rate: on the Open ASR Leaderboard snapshot of 2026-09-25, the lowest seven-set averages (Zoom Scribe v2 Pro 3.68 %, Modulate 3.92 %, Azure Speech 3.93 %) are closed APIs, against 4.29 % for the best open row.
- No one on the team wants to run a service.

## When self-hosting is the better choice

- Steady volume: at our measured $0.00204 per audio hour, 100,000 audio hours cost about $204 of GPU and gateway time.
- Audio that cannot leave your environment for legal or contractual reasons. The model runs in your cloud, data centre or on the device.
- Hardware you already own: Phonon-2 runs at 143 times realtime on eight AMD Zen 5 cores (Phonon-2's published figure), so an ordinary CPU server can transcribe more than a hundred hours of audio per hour.
- Control: a fixed model version, no deprecations, and the ability to re-run any benchmark yourself.

```text
pip install fermion-research
fermion serve phonon-2.5 --host 0.0.0.0 --port 8000 --api-key "$FERMION_API_KEY"
```

## A simple way to decide

Estimate monthly audio hours. Multiply by the API price you would pay, then compare with the monthly cost of the smallest server that handles your peak load plus a few hours a month of someone's time to run it. If the API bill is the smaller number, use the API and revisit when volume grows. If audio cannot leave your environment, self-host regardless of the arithmetic.

## Questions

## Related

- [Speech-to-text API cost](https://www.fermionresearch.com/speech/speech-to-text-api-cost/)
- [Self-host a speech-to-text server](https://www.fermionresearch.com/models/phonon-2-5/self-host/)
- [On-device speech recognition for regulated teams](https://www.fermionresearch.com/deploy/on-device-speech-recognition/)
- [Server docs](https://www.fermionresearch.com/docs/serve/)
- [Deploy with Fermion](https://www.fermionresearch.com/deploy/)

## Sources and method

- Self-hosting cost: Fermion Research measurement of Phonon-2 on an NVIDIA L4 staging server, 2026-10-08, realistic audio mix, GPU plus gateway, 60 % utilisation.
- Hosted list prices marked OpenRouter: OpenRouter speech-to-text model pages, read 2026-11-11.
- Vendor prices and features read 2026-11-13: deepgram.com/pricing, assemblyai.com/pricing, elevenlabs.io/pricing/api, developers.openai.com/api/docs/pricing.
- Rival English averages: Open ASR Leaderboard, seven English sets (LibriSpeech clean and other, AMI, Earnings-22, GigaSpeech, SPGISpeech, VoxPopuli), snapshot 2026-09-25.
- Phonon-2 CPU speed: Phonon-2 model page, published figure. No Phonon-2.5 speed figures are published.

Canonical: https://www.fermionresearch.com/speech/self-hosted-vs-api-speech-to-text/

Source: [https://www.fermionresearch.com/speech/self-hosted-vs-api-speech-to-text/](https://www.fermionresearch.com/speech/self-hosted-vs-api-speech-to-text/)
