FunASR / SenseVoice (Alibaba) Review

OSS

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

Facts verified Jul 20, 2026Website →

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.

Reviewed by vsref Editorialfacts verified Jul 20, 2026Methodology →

Fact sheet

Every row independently verified

Pricing

Pricing facts
Free tier quota	Unlimited (self-hosted, free)	Jul 20

Capabilities

Capabilities facts
WER (vendor-claimed)	~7.81 % WER	Jul 20
Languages supported	~5	Jul 20
Language auto-detection	✓ Yes	Jul 20
Speaker diarization	✓ Included	Jul 20
PII redaction	✗ Not available	Jul 20
Word-level timestamps	✓ Yes	Jul 20
Custom vocabulary / keyterm boosting	✓ Yes	Jul 20
Entity detection	✗ No	Jul 20
Sentiment analysis	✓ Yes	Jul 20
Summarization endpoint	✗ No	Jul 20
Speech translation	✗ No	Jul 20
Priced audio-intelligence add-ons	Emotion recog, audio event detect, LID	Jul 20

Compliance & trust

Compliance & trust facts
HIPAA BAA available	✗ Not available	Jul 20
SOC 2 Type II	✗ No	Jul 20
GDPR / EU data residency	✗ No	Jul 20
Self-host / on-prem option	✓ Yes	Jul 20
Model weights license	FunASR Model Open Source License	Jul 20

Build experience

Build experience facts
Official SDKs	Python; C++/ONNX runtime; llama.cpp GGUF	Jul 20
Websocket streaming API	✓ Yes	Jul 20

Commercial

Commercial facts
Model size (parameters)	SenseVoiceSmall 234M; Paraformer 220M	Jul 20
Hardware to self-host	CPU or GPU; SenseVoice ~17x realtime on CPU	Jul 20
Hosted API available	No; self-host (OpenAI-compatible server)	Jul 20
Project maintenance status	Active - v1.3.22 released 2026-07	Jul 20
GitHub stars	19,400	Jul 20

Considering a switch? Best FunASR / SenseVoice (Alibaba) alternatives →

Voice agents in this stack

The engine is one layer: a voice agent hears through its transcription engine, but orchestration, telephony, and turn-taking come from the agent platform. Compare the platforms builders pair FunASR / SenseVoice (Alibaba) with: Pipecat, OpenAI Realtime API, Twilio ConversationRelay, or the full voice-agent comparison →

Want it done for you?

FunASR / SenseVoice (Alibaba) gets you a transcript; the bot that joins the call, labels speakers, and writes the summary is still your build. If that is more pipeline than you want to own, AI meeting notetakers do the whole job end to end: Otter.ai, Fireflies.ai, Fathom, or the full notetaker comparison.