# Best Speech-to-text APIs for Dictation (2026)

> The best Speech-to-text APIs platforms for dictation: Moonshine leads, for voice typing on your own computer: which apps work where, whether audio leaves the.

For dictation, **Moonshine** is our pick: For voice typing on your own computer, local processing is the dominant concern because users want audio to stay on device. Voice typing on your own computer: which apps work where, whether audio leaves the device, and what the pricing model really is. Below is the full ranking and the tradeoffs, or read [how we score](https://www.versusref.com/methodology/).

## What matters for dictation

Weight ×5 = decisive, ×1 = relevant.

| Fact | Weight | Moonshine | NVIDIA Parakeet / Riva | Deepgram | AssemblyAI | ElevenLabs Scribe |
| --- | --- | --- | --- | --- | --- | --- |
| Platforms | ×5 | n/a | n/a | n/a | n/a | n/a |
| Local vs cloud processing | ×4 | n/a | n/a | n/a | n/a | n/a |
| AI formatting / edit features | ×4 | n/a | n/a | n/a | n/a | n/a |
| App pricing (one-time vs subscription) | ×3 | n/a | n/a | n/a | n/a | n/a |
| App integrations | ×3 | n/a | n/a | n/a | n/a | n/a |

- ×5 **Platforms:** An app that does not run on your OS is out, whatever else it does.
- ×4 **Local vs cloud processing:** On-device transcription keeps your words off vendor servers and works offline.
- ×4 **AI formatting / edit features:** Auto-punctuation and cleanup are what separate dictation from raw transcription.
- ×3 **App pricing (one-time vs subscription):** One-time licenses and subscriptions price out very differently over a year of use.
- ×3 **App integrations:** System-wide dictation beats an app you have to copy-paste out of.

## The ranking, tool by tool

| Rank | Tool | Verdict | Score | Price |
| --- | --- | --- | --- | --- |
| 1 | [Moonshine](https://www.versusref.com/stt/tools/moonshine/) (OSS) | For voice typing on your own computer, local processing is the dominant concern because users want audio to stay on device. | 2 of 2 points · 1 matchup | See pricing |
| 2 | [NVIDIA Parakeet / Riva](https://www.versusref.com/stt/tools/nvidia-parakeet/) | For voice typing on your own computer, local processing is the top priority after platform fit. | 1.5 of 4 points · 2 matchups | See pricing |
| 3 | [Deepgram](https://www.versusref.com/stt/tools/deepgram/) | Developer-first realtime STT API for voice agents and transcription at scale. | 8.5 of 34 points · 17 matchups | See pricing |
| 4 | [AssemblyAI](https://www.versusref.com/stt/tools/assemblyai/) | Accuracy-led voice AI API for developers and voice agents. | 3.5 of 14 points · 7 matchups | See pricing |
| 5 | [ElevenLabs Scribe](https://www.versusref.com/stt/tools/elevenlabs-scribe/) | Accuracy-led STT API from the leading AI audio company. | 2 of 8 points · 4 matchups | From $6/mo |
| 6 | [Gladia](https://www.versusref.com/stt/tools/gladia/) | EU-based real-time and batch STT API built on the Solaria models. | 1.5 of 6 points · 3 matchups | See pricing |
| 7 | [Google Cloud Speech-to-Text](https://www.versusref.com/stt/tools/google-stt/) | Hyperscaler STT API with Chirp foundation models and enterprise compliance. | 1.5 of 6 points · 3 matchups | See pricing |
| 8 | [Mistral Voxtral Transcribe](https://www.versusref.com/stt/tools/voxtral/) | Low-cost EU-based transcription API with Apache-2.0 open-weight models. | 1.5 of 6 points · 3 matchups | See pricing |
| 9 | [Amazon Transcribe](https://www.versusref.com/stt/tools/amazon-transcribe/) | AWS-native STT API with deep AWS ecosystem integration and compliance coverage. | 1 of 4 points · 2 matchups | See pricing |
| 10 | [Azure AI Speech (STT)](https://www.versusref.com/stt/tools/azure-speech/) | Enterprise-grade STT inside the Azure cloud ecosystem. | 1 of 4 points · 2 matchups | From $1,600/mo |
| 11 | [Rev AI](https://www.versusref.com/stt/tools/rev/) | Transcription-heritage STT API with low per-hour pricing and open (non-commercial) Reverb models. | 1 of 4 points · 2 matchups | See pricing |
| 12 | [Soniox](https://www.versusref.com/stt/tools/soniox/) | Ultra-low-cost multilingual STT + real-time translation API. | 1 of 4 points · 2 matchups | See pricing |
| 13 | [Speechmatics](https://www.versusref.com/stt/tools/speechmatics/) | Accuracy-first enterprise STT with flexible deployment (SaaS, container, on-prem). | 1 of 4 points · 2 matchups | See pricing |
| 14 | [Cartesia Ink](https://www.versusref.com/stt/tools/cartesia-ink/) | Streaming STT for voice agents with native turn detection. | 0.5 of 2 points · 1 matchup | From $5/mo |
| 15 | [Cohere Transcribe](https://www.versusref.com/stt/tools/cohere-transcribe/) | Enterprise-grade open ASR for accurate batch transcription. | 0.5 of 2 points · 1 matchup | See pricing |
| 16 | [OpenAI gpt-4o-transcribe](https://www.versusref.com/stt/tools/gpt-4o-transcribe/) | Flagship GPT-4o based transcription API from OpenAI. | 0.5 of 2 points · 1 matchup | See pricing |
| 17 | [xAI Grok Speech-to-Text](https://www.versusref.com/stt/tools/grok-stt/) | Low-cost hosted STT API on the Grok stack. | 0.5 of 2 points · 1 matchup | See pricing |
| 18 | [Groq (hosted Whisper)](https://www.versusref.com/stt/tools/groq-whisper/) | Ultra-fast, low-cost hosted Whisper transcription API (no realtime streaming). | 0.5 of 2 points · 1 matchup | See pricing |
| 19 | [IBM watsonx Speech to Text](https://www.versusref.com/stt/tools/ibm-watson-stt/) | Enterprise cloud STT API. | 0.5 of 2 points · 1 matchup | See pricing |
| 20 | [Qwen3-ASR](https://www.versusref.com/stt/tools/qwen3-asr/) (OSS) | Open-weights multilingual ASR models. | 0.5 of 2 points · 1 matchup | See pricing |
| 21 | [Smallest.ai Pulse](https://www.versusref.com/stt/tools/smallest-pulse/) | Ultra-low-latency multilingual STT for voice agents. | 0.5 of 2 points · 1 matchup | See pricing |
| 22 | [OpenAI Whisper (API)](https://www.versusref.com/stt/tools/whisper/) | Low-cost pay-as-you-go file transcription from OpenAI; no first-party streaming or diarization. | 4 of 20 points · 10 matchups | See pricing |

### 1. Moonshine

For voice typing on your own computer, local processing is the dominant concern because users want audio to stay on device. [Full Moonshine vs OpenAI Whisper (API) verdict](https://www.versusref.com/stt/moonshine-vs-whisper/)

### 2. NVIDIA Parakeet / Riva

For voice typing on your own computer, local processing is the top priority after platform fit. [Full NVIDIA Parakeet / Riva vs OpenAI Whisper (API) verdict](https://www.versusref.com/stt/nvidia-parakeet-vs-whisper/)

### 3. Deepgram

Developer-first realtime STT API for voice agents and transcription at scale. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 4. AssemblyAI

Accuracy-led voice AI API for developers and voice agents. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 5. ElevenLabs Scribe

Accuracy-led STT API from the leading AI audio company. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 6. Gladia

EU-based real-time and batch STT API built on the Solaria models. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 7. Google Cloud Speech-to-Text

Hyperscaler STT API with Chirp foundation models and enterprise compliance. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 8. Mistral Voxtral Transcribe

Low-cost EU-based transcription API with Apache-2.0 open-weight models. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 9. Amazon Transcribe

AWS-native STT API with deep AWS ecosystem integration and compliance coverage. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 10. Azure AI Speech (STT)

Enterprise-grade STT inside the Azure cloud ecosystem. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 11. Rev AI

Transcription-heritage STT API with low per-hour pricing and open (non-commercial) Reverb models. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 12. Soniox

Ultra-low-cost multilingual STT + real-time translation API. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 13. Speechmatics

Accuracy-first enterprise STT with flexible deployment (SaaS, container, on-prem). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 14. Cartesia Ink

Streaming STT for voice agents with native turn detection. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 15. Cohere Transcribe

Enterprise-grade open ASR for accurate batch transcription. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 16. OpenAI gpt-4o-transcribe

Flagship GPT-4o based transcription API from OpenAI. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 17. xAI Grok Speech-to-Text

Low-cost hosted STT API on the Grok stack. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 18. Groq (hosted Whisper)

Ultra-fast, low-cost hosted Whisper transcription API (no realtime streaming). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 19. IBM watsonx Speech to Text

Enterprise cloud STT API. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 20. Qwen3-ASR

Open-weights multilingual ASR models. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 21. Smallest.ai Pulse

Ultra-low-latency multilingual STT for voice agents. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 22. OpenAI Whisper (API)

Low-cost pay-as-you-go file transcription from OpenAI; no first-party streaming or diarization. No won verdicts for this use case yet; it ranks on ties and near-misses.

Source: https://www.versusref.com/stt/best/dictation/