# FunASR / SenseVoice (Alibaba) Review

> FunASR / SenseVoice (Alibaba) review: Open-source industrial ASR toolkit. Verified pricing, features, and the strongest alternatives in Speech-to-text APIs.

![FunASR / SenseVoice (Alibaba) logo](https://www.versusref.com/logos/funasr.png)

Open-source industrial ASR toolkit

Among the 43 speech-to-text tools we track, FunASR / SenseVoice (Alibaba) has the 40th-widest language coverage.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about FunASR / SenseVoice (Alibaba)

This is our verified profile of FunASR / SenseVoice (Alibaba), a speech-to-text apis platform - open-source industrial ASR toolkit. Every fact about FunASR / SenseVoice (Alibaba) below carries the source it came from and the day we checked it.

FunASR / SenseVoice (Alibaba) does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current FunASR / SenseVoice (Alibaba) quote, it is the fastest way for us to close that gap.

On capabilities, FunASR / SenseVoice (Alibaba) covers language auto-detection, word-level timestamps, custom vocabulary / keyterm boosting, sentiment analysis, self-host / on-prem option, and websocket streaming api, and does not offer entity detection, summarization endpoint, and speech translation. Each of those is verified against FunASR / SenseVoice (Alibaba)'s own docs or dashboard, not marketing copy.

For compliance, with FunASR / SenseVoice (Alibaba): SOC 2 Type II is not reported. If you are in a regulated space, confirm the current posture with FunASR / SenseVoice (Alibaba) before you commit, since these change plan by plan.

Among the 43 speech-to-text tools in our matrix, FunASR / SenseVoice (Alibaba) leads with the 40th-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 25 verified facts for FunASR / SenseVoice (Alibaba) 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 FunASR / SenseVoice (Alibaba) fact sheet below.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Free tier quota | Unlimited (self-hosted, free) | Jul 20 | [source](https://github.com/modelscope/FunASR) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| WER (vendor-claimed) | ~7.81 % WER | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Languages supported | ~5 | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |
| Language auto-detection | ✓  Yes | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |
| Speaker diarization | ✓  Included | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| PII redaction | ✗  Not available | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Word-level timestamps | ✓  Yes | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |
| Custom vocabulary / keyterm boosting | ✓  Yes | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Entity detection | ✗  No | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Sentiment analysis | ✓  Yes | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |
| Summarization endpoint | ✗  No | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Speech translation | ✗  No | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |
| Priced audio-intelligence add-ons | Emotion recog, audio event detect, LID | Jul 20 | [source](https://github.com/FunAudioLLM/SenseVoice/blob/main/README.md) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| HIPAA BAA available | ✗  Not available | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| SOC 2 Type II | ✗  No | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| GDPR / EU data residency | ✗  No | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Model weights license | FunASR Model Open Source License | Jul 20 | [source](https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python; C++/ONNX runtime; llama.cpp GGUF | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Websocket streaming API | ✓  Yes | Jul 20 | [source](https://github.com/modelscope/FunASR) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | SenseVoiceSmall 234M; Paraformer 220M | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Hardware to self-host | CPU or GPU; SenseVoice ~17x realtime on CPU | Jul 20 | [source](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) |
| Hosted API available | No; self-host (OpenAI-compatible server) | Jul 20 | [source](https://github.com/modelscope/FunASR) |
| Project maintenance status | Active - v1.3.22 released 2026-07 | Jul 20 | [source](https://github.com/modelscope/FunASR/releases) |
| GitHub stars | 19,400 | Jul 20 | [source](https://github.com/modelscope/FunASR) |

Source: https://www.versusref.com/stt/tools/funasr/