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

> The best Speech-to-text APIs platforms for medical: AssemblyAI leads, for clinical transcription under us healthcare privacy law: a hipaa baa is the gate, and.

For medical, **AssemblyAI** is our pick: Both tools offer a HIPAA BAA and SOC 2 Type II certification, so the top criteria are matched. Clinical transcription under US healthcare privacy law: a HIPAA BAA is the gate, and medical vocabulary decides accuracy. Below is the full ranking and the tradeoffs, or read [how we score](https://www.versusref.com/methodology/).

## What matters for medical

Weight ×5 = decisive, ×1 = relevant.

| Fact | Weight | AssemblyAI | Deepgram | OpenAI Whisper (API) | Amazon Transcribe | Gladia |
| --- | --- | --- | --- | --- | --- | --- |
| HIPAA BAA available | ×5 | ✓  Included (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) |
| PII redaction | ×4 | ◑  Paid add-on (Jul 20) | ◑  Paid add-on (Jul 20) | ✗  Not available (Jul 20) | ◑  Paid add-on (Jul 20) | ✓  Included (Jul 20) |
| Custom vocabulary / keyterm boosting | ×4 | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) |
| SOC 2 Type II | ×3 | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) |
| Self-host / on-prem option | ×2 | ✓  Yes (Jul 20) | ✓  Yes (Jul 20) | ✗  No (Jul 20) | ✗  No (Jul 20) | ✓  Yes (Jul 20) |

- ×5 **HIPAA BAA available:** Without a signed BAA, patient audio cannot legally touch the service; this is a hard filter, not a preference.
- ×4 **PII redaction:** Removing patient identifiers from stored transcripts is a compliance requirement, not a nicety.
- ×4 **Custom vocabulary / keyterm boosting:** Drug names and clinical terms are where general models fail; vocabulary boosting closes the gap.
- ×3 **SOC 2 Type II:** Healthcare procurement asks for the audit report before the pilot starts.
- ×2 **Self-host / on-prem option:** Some health systems only clear tools that run inside their own perimeter.

## The ranking, tool by tool

| Rank | Tool | Verdict | Score | Price |
| --- | --- | --- | --- | --- |
| 1 | [AssemblyAI](https://www.versusref.com/stt/tools/assemblyai/) | Both tools offer a HIPAA BAA and SOC 2 Type II certification, so the top criteria are matched. | 9 of 14 points · 7 matchups | See pricing |
| 2 | [Deepgram](https://www.versusref.com/stt/tools/deepgram/) | For clinical transcription under US healthcare privacy law, the HIPAA BAA is the absolute gate. | 16.5 of 26 points · 13 matchups | See pricing |
| 3 | [OpenAI Whisper (API)](https://www.versusref.com/stt/tools/whisper/) | A HIPAA BAA is the gate for this use case, and only OpenAI Whisper has a verified HIPAA BAA available. | 10.5 of 20 points · 10 matchups | See pricing |
| 4 | [Amazon Transcribe](https://www.versusref.com/stt/tools/amazon-transcribe/) | Both tools offer a HIPAA BAA and SOC 2 Type II certification, so the top and fourth-ranked attributes are tied. | 1 of 2 points · 1 matchup | See pricing |
| 5 | [Gladia](https://www.versusref.com/stt/tools/gladia/) | Both Gladia and OpenAI Whisper (API) offer a HIPAA BAA, clearing that gate requirement equally. | 1.5 of 6 points · 3 matchups | See pricing |
| 6 | [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 |
| 7 | [Mistral Voxtral Transcribe](https://www.versusref.com/stt/tools/voxtral/) | For clinical transcription under US healthcare privacy law, the HIPAA BAA requirement is the decisive gate. | 1 of 6 points · 3 matchups | See pricing |
| 8 | [Azure AI Speech (STT)](https://www.versusref.com/stt/tools/azure-speech/) | Enterprise-grade STT inside the Azure cloud ecosystem. | 0.5 of 4 points · 2 matchups | From $1,600/mo |
| 9 | [Google Cloud Speech-to-Text](https://www.versusref.com/stt/tools/google-stt/) | Hyperscaler STT API with Chirp foundation models and enterprise compliance. | 0.5 of 6 points · 3 matchups | See pricing |
| 10 | [Cartesia Ink](https://www.versusref.com/stt/tools/cartesia-ink/) | Streaming STT for voice agents with native turn detection. | 0 of 2 points · 1 matchup | From $5/mo |
| 11 | [Cohere Transcribe](https://www.versusref.com/stt/tools/cohere-transcribe/) | Enterprise-grade open ASR for accurate batch transcription. | 0 of 2 points · 1 matchup | See pricing |
| 12 | [ElevenLabs Scribe](https://www.versusref.com/stt/tools/elevenlabs-scribe/) | Accuracy-led STT API from the leading AI audio company. | 0 of 6 points · 3 matchups | From $6/mo |
| 13 | [xAI Grok Speech-to-Text](https://www.versusref.com/stt/tools/grok-stt/) | Low-cost hosted STT API on the Grok stack. | 0 of 2 points · 1 matchup | See pricing |
| 14 | [Groq (hosted Whisper)](https://www.versusref.com/stt/tools/groq-whisper/) | Ultra-fast, low-cost hosted Whisper transcription API (no realtime streaming). | 0 of 2 points · 1 matchup | See pricing |
| 15 | [Moonshine](https://www.versusref.com/stt/tools/moonshine/) (OSS) | On-device streaming STT for live voice interfaces, from tiny edge models to Whisper Large v3-beating accuracy. | 0 of 2 points · 1 matchup | See pricing |
| 16 | [NVIDIA Parakeet / Riva](https://www.versusref.com/stt/tools/nvidia-parakeet/) | Open-weights, GPU-accelerated self-hosted STT stack. | 0 of 4 points · 2 matchups | See pricing |
| 17 | [Qwen3-ASR](https://www.versusref.com/stt/tools/qwen3-asr/) (OSS) | Open-weights multilingual ASR models. | 0 of 2 points · 1 matchup | See pricing |
| 18 | [Rev AI](https://www.versusref.com/stt/tools/rev/) | Transcription-heritage STT API with low per-hour pricing and open (non-commercial) Reverb models. | 0 of 2 points · 1 matchup | See pricing |
| 19 | [Smallest.ai Pulse](https://www.versusref.com/stt/tools/smallest-pulse/) | Ultra-low-latency multilingual STT for voice agents. | 0 of 2 points · 1 matchup | See pricing |
| 20 | [Soniox](https://www.versusref.com/stt/tools/soniox/) | Ultra-low-cost multilingual STT + real-time translation API. | 0 of 4 points · 2 matchups | See pricing |
| 21 | [Speechmatics](https://www.versusref.com/stt/tools/speechmatics/) | Accuracy-first enterprise STT with flexible deployment (SaaS, container, on-prem). | 0 of 4 points · 2 matchups | See pricing |

### 1. AssemblyAI

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so the top criteria are matched. [Full AssemblyAI vs OpenAI Whisper (API) verdict](https://www.versusref.com/stt/assemblyai-vs-whisper/)

Both tools offer a HIPAA BAA, SOC 2 Type II, custom vocabulary, and self-host options, so those attributes do not separate them. [Full AssemblyAI vs Speechmatics verdict](https://www.versusref.com/stt/assemblyai-vs-speechmatics/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, making them equal on the two highest-weighted compliance requirements. [Full AssemblyAI vs Soniox verdict](https://www.versusref.com/stt/assemblyai-vs-soniox/)

For clinical transcription under US healthcare privacy law, the HIPAA BAA is the decisive gate. [Full AssemblyAI vs Rev AI verdict](https://www.versusref.com/stt/assemblyai-vs-rev/)

For clinical transcription under US healthcare privacy law, the HIPAA BAA is the absolute gate. [Full AssemblyAI vs ElevenLabs Scribe verdict](https://www.versusref.com/stt/assemblyai-vs-elevenlabs-scribe/)

### 2. Deepgram

For clinical transcription under US healthcare privacy law, the HIPAA BAA is the absolute gate. [Full Deepgram vs Smallest.ai Pulse verdict](https://www.versusref.com/stt/deepgram-vs-smallest-pulse/)

Both tools offer a HIPAA BAA, clearing the compliance gate equally. [Full Deepgram vs Azure AI Speech (STT) verdict](https://www.versusref.com/stt/azure-speech-vs-deepgram/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the absolute gate requirement. [Full Deepgram vs Mistral Voxtral Transcribe verdict](https://www.versusref.com/stt/deepgram-vs-voxtral/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the non-negotiable requirement. [Full Deepgram vs NVIDIA Parakeet / Riva verdict](https://www.versusref.com/stt/deepgram-vs-nvidia-parakeet/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so neither leads on those two compliance attributes. [Full Deepgram vs xAI Grok Speech-to-Text verdict](https://www.versusref.com/stt/deepgram-vs-grok-stt/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so those attributes are tied. [Full Deepgram vs OpenAI Whisper (API) verdict](https://www.versusref.com/stt/deepgram-vs-whisper/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so they tie on the two heaviest compliance attributes. [Full Deepgram vs Speechmatics verdict](https://www.versusref.com/stt/deepgram-vs-speechmatics/)

Both tools clear the HIPAA BAA gate, so the decision falls to lower-ranked attributes. [Full Deepgram vs Soniox verdict](https://www.versusref.com/stt/deepgram-vs-soniox/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so those top-weighted attributes are tied. [Full Deepgram vs Google Cloud Speech-to-Text verdict](https://www.versusref.com/stt/deepgram-vs-google-stt/)

Both tools offer a HIPAA BAA, SOC 2 Type II, and self-host options, so those attributes do not differentiate them. [Full Deepgram vs Gladia verdict](https://www.versusref.com/stt/deepgram-vs-gladia/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the mandatory gate. [Full Deepgram vs Cohere Transcribe verdict](https://www.versusref.com/stt/cohere-transcribe-vs-deepgram/)

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so they tie on the two highest-weighted compliance attributes. [Full Deepgram vs Cartesia Ink verdict](https://www.versusref.com/stt/cartesia-ink-vs-deepgram/)

### 3. OpenAI Whisper (API)

A HIPAA BAA is the gate for this use case, and only OpenAI Whisper has a verified HIPAA BAA available. [Full OpenAI Whisper (API) vs Mistral Voxtral Transcribe verdict](https://www.versusref.com/stt/voxtral-vs-whisper/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the absolute requirement. [Full OpenAI Whisper (API) vs Qwen3-ASR verdict](https://www.versusref.com/stt/qwen3-asr-vs-whisper/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the absolute gate. [Full OpenAI Whisper (API) vs NVIDIA Parakeet / Riva verdict](https://www.versusref.com/stt/nvidia-parakeet-vs-whisper/)

For clinical transcription under US healthcare privacy law, a HIPAA BAA is the absolute gate. [Full OpenAI Whisper (API) vs Moonshine verdict](https://www.versusref.com/stt/moonshine-vs-whisper/)

The heaviest attribute for clinical transcription under US healthcare privacy law is HIPAA BAA availability. [Full OpenAI Whisper (API) vs Groq (hosted Whisper) verdict](https://www.versusref.com/stt/groq-whisper-vs-whisper/)

The heaviest factor is HIPAA BAA availability. [Full OpenAI Whisper (API) vs ElevenLabs Scribe verdict](https://www.versusref.com/stt/elevenlabs-scribe-vs-whisper/)

### 4. Amazon Transcribe

Both tools offer a HIPAA BAA and SOC 2 Type II certification, so the top and fourth-ranked attributes are tied. [Full Amazon Transcribe vs Google Cloud Speech-to-Text verdict](https://www.versusref.com/stt/amazon-transcribe-vs-google-stt/)

### 5. Gladia

Both Gladia and OpenAI Whisper (API) offer a HIPAA BAA, clearing that gate requirement equally. [Full Gladia vs OpenAI Whisper (API) verdict](https://www.versusref.com/stt/gladia-vs-whisper/)

### 6. 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.

### 7. Mistral Voxtral Transcribe

For clinical transcription under US healthcare privacy law, the HIPAA BAA requirement is the decisive gate. [Full Mistral Voxtral Transcribe vs ElevenLabs Scribe verdict](https://www.versusref.com/stt/elevenlabs-scribe-vs-voxtral/)

### 8. 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.

### 9. 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.

### 10. 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.

### 11. 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.

### 12. 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.

### 13. 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.

### 14. 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.

### 15. Moonshine

On-device streaming STT for live voice interfaces, from tiny edge models to Whisper Large v3-beating accuracy. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 16. NVIDIA Parakeet / Riva

Open-weights, GPU-accelerated self-hosted STT stack. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 17. Qwen3-ASR

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

### 18. 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.

### 19. 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.

### 20. 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.

### 21. 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.

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