vsref
faster-whisper / whisper.cpp logo

faster-whisper / whisper.cpp Review

OSS

The de facto local Whisper runtimes: faster-whisper (Python/CTranslate2) and whisper.cpp (C/C++)

Among the 43 speech-to-text tools we track, faster-whisper / whisper.cpp has the 12th-widest language coverage - a fit for multilingual and localization projects.

See pricing

Facts verified Jul 20, 2026Website →

What we know about faster-whisper / whisper.cpp

faster-whisper / whisper.cpp is a speech-to-text apis platform: the de facto local Whisper runtimes: faster-whisper (Python/CTranslate2) and whisper.cpp (C/C++). This profile tracks every faster-whisper / whisper.cpp fact we have verified, each linked to a primary source and dated.

faster-whisper / whisper.cpp 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 faster-whisper / whisper.cpp quote, it is the fastest way for us to close that gap.

On capabilities, faster-whisper / whisper.cpp covers language auto-detection, word-level timestamps, custom vocabulary / keyterm boosting, speech translation, gdpr / eu data residency, and self-host / on-prem option, and does not offer entity detection, sentiment analysis, and summarization endpoint. Each of those is verified against faster-whisper / whisper.cpp's own docs or dashboard, not marketing copy.

Among the 43 speech-to-text tools in our matrix, faster-whisper / whisper.cpp leads with the 12th-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 21 verified facts for faster-whisper / whisper.cpp 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 faster-whisper / whisper.cpp fact sheet below.

Reviewed by vsref Editorialfacts verified Jul 20, 2026Methodology →

Fact sheet

Capabilities
Capabilities facts
Languages supported99 languagesJul 20
Language auto-detection✓ YesJul 20
Speaker diarization✗ Not availableJul 20
PII redaction✗ Not availableJul 20
Word-level timestamps✓ YesJul 20
Custom vocabulary / keyterm boosting✓ YesJul 20
Entity detection✗ NoJul 20
Sentiment analysis✗ NoJul 20
Summarization endpoint✗ NoJul 20
Speech translation✓ YesJul 20
Compliance & trust
Compliance & trust facts
GDPR / EU data residency✓ YesJul 20
Self-host / on-prem option✓ YesJul 20
Model weights licenseMITJul 20
Build experience
Build experience facts
Official SDKsPython (faster-whisper)Jul 20
Supported audio formatsAny FFmpeg-decodable audio (faster-whisper via PyAV)Jul 20
Websocket streaming API✗ NoJul 20
Commercial
Commercial facts
Model size (parameters)39M (tiny) to 1.55B (large-v3); turbo 809MJul 20
Hardware to self-hostCPU-capableJul 20
Project maintenance statusActive - faster-whisper v1.2.1 released 2025-10-31Jul 20
GitHub stars24,400 starsJul 20
Local vs cloud processingLocal (on-device)Jul 20

Considering a switch? Best faster-whisper / whisper.cpp 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 faster-whisper / whisper.cpp with: Pipecat, OpenAI Realtime API, Twilio ConversationRelay, or the full voice-agent comparison →

Want it done for you?

faster-whisper / whisper.cpp 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.