# Gradium Speech-to-Text Review

> Gradium Speech-to-Text review: Low-latency STT for voice agents. Verified pricing, features, and the strongest alternatives in Speech-to-text APIs.

![Gradium Speech-to-Text logo](https://www.versusref.com/logos/gradium-stt.png)

Low-latency STT for voice agents

Among the 43 speech-to-text tools we track, Gradium Speech-to-Text has the 40th-widest language coverage.

From $13/mo · facts verified Jul 20, 2026

## What we know about Gradium Speech-to-Text

This is our verified profile of Gradium Speech-to-Text, a speech-to-text apis platform - low-latency STT for voice agents. Every fact about Gradium Speech-to-Text below carries the source it came from and the day we checked it.

On pricing, Gradium Speech-to-Text starts at $13 per month for its entry tier. That is the sticker rate: real production cost usually runs higher once you add a language model, a voice provider, and telephony minutes.

On capabilities, Gradium Speech-to-Text covers speech translation and websocket streaming api, and does not offer language auto-detection, word-level timestamps, and custom vocabulary / keyterm boosting. Each of those is verified against Gradium Speech-to-Text's own docs or dashboard, not marketing copy.

Placed against the 43 speech-to-text tools we track, Gradium Speech-to-Text's strongest showing is the 40th-widest language coverage - a spread worth weighing against your own priorities.

In total we track 23 verified facts for Gradium Speech-to-Text today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Gradium Speech-to-Text fact sheet below.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Pricing model | hybrid | Jul 20 | [source](https://gradium.ai/pricing) |
| Cheapest paid plan | $13 | Jul 20 | [source](https://gradium.ai/pricing) |
| Free tier quota | 45k credits (~4 hrs STT) | Jul 20 | [source](https://gradium.ai/pricing) |
| Published volume discounts | Yes - add-on credits cheaper at higher tiers | Jul 20 | [source](https://gradium.ai/pricing) |
| Concurrency on base plan | Free 3; XS/S 20 sessions | Jul 20 | [source](https://gradium.ai/pricing) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| WER (third-party benchmark) | 8.38 % WER | Jul 20 | [source](https://artificialanalysis.ai/speech-to-text) |
| Streaming latency (vendor-claimed) | ~300 ms | Jul 20 | [source](https://docs.gradium.ai/guides/introduction) |
| Languages supported | 5 | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Language auto-detection | ✗  No | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Speaker diarization | ✗  Not available | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| PII redaction | ✗  Not available | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Word-level timestamps | ✗  No | Jul 20 | [source](https://docs.gradium.ai/guides/speech-to-text) |
| Custom vocabulary / keyterm boosting | ✗  No | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Entity detection | ✗  Not offered. | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Sentiment analysis | ✗  Not offered. | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Summarization endpoint | ✗  Not offered. | Jul 20 | [source](https://docs.gradium.ai/guides/transcription-settings) |
| Speech translation | ✓  Yes | Jul 20 | [source](https://docs.gradium.ai/guides/speech-to-text-overview) |
| Priced audio-intelligence add-ons | None (semantic VAD, translation only) | Jul 20 | [source](https://docs.gradium.ai/guides/speech-to-text-overview) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✗  No | Jul 20 | [source](https://docs.gradium.ai/api-reference/introduction) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python (pip install gradium) | Jul 20 | [source](https://docs.gradium.ai/guides/installation) |
| Max file size / duration | 300 s per session (5 min) | Jul 20 | [source](https://docs.gradium.ai/guides/limits) |
| Supported audio formats | WAV, PCM, Opus, mu-law, A-law | Jul 20 | [source](https://docs.gradium.ai/guides/limits) |
| Websocket streaming API | ✓  Yes | Jul 20 | [source](https://docs.gradium.ai/guides/speech-to-text) |

Source: https://www.versusref.com/stt/tools/gradium-stt/