faster-whisper
A free tool that turns speech into text. It's for people making images, video, or audio. It's free.
Get patch notes
Same daily newsletter as the rest of the site. One email a day.
No affiliate link on file. Outbound goes to github.com. Identity checked October 21, 2026. Score null is from the run on October 21, 2026.
Grade
We tried it ourselves. Grade A.
- Grade
- A · We tried it
- Score
- 8/10
- Price
- Free
Best for
Jobs people use this for.
Test details
Fast Whisper speech-to-text on CTranslate2, on CPU or GPU. MIT license.
Hands-on review · 2026-10-21
TestedA8/10- CPU-only box: 8 cores, 15 GB RAM, no GPU.
- Synthetic audio only
faster-whisper was fast and accurate. Even the tiny model transcribed 12 seconds of speech in under half a second on CPU, and the only consistent 'error' was splitting the brand name. A fresh install crashed until we pinned PyAV, which will trip up newcomers. We only used clean synthetic audio, so noisy real-world recordings are untested.
Very fast and accurate on CPU. Fresh-install crash and clean-audio-only test cost points.
- Coverage
- WER and speed on two synthetic clips, three English models
- What we tested
- Transcription accuracy (WER) and speed on two TTS-generated clips (Piper and Kokoro, 11.5 s and 12.8 s) with tiny.en, base.en and small.en.
Method
faster-whisper 1.2.1, CPU int8, beam 5. Reference is the known script, normalized to lowercase alphanumerics.
Measured
- install_issueA fresh install pulled PyAV 19.0.2 and transcribe() crashed (TypeError metadata_errors). Fixed by pinning av<17
- tiny.en pipertranscribe 0.46 s, rtf 0.04, wer 0.091
- tiny.en kokorotranscribe 0.38 s, rtf 0.03, wer 0.061
- base.en pipertranscribe 0.63 s, rtf 0.055, wer 0.061
- base.en kokorotranscribe 0.88 s, rtf 0.069, wer 0.061
- small.en pipertranscribe 1.5 s, rtf 0.131, wer 0.061
- small.en kokorotranscribe 1.64 s, rtf 0.128, wer 0.061
- noteThe 0.061 WER floor is entirely 'AgentTested' being transcribed as two words. Everything else matched.
Pros
- Real-time factor 0.03-0.13 on CPU (30x to 8x faster than real time)
- Near-perfect transcripts even with tiny.en
Cons
- Out of the box, the dependency mismatch crashed transcription
- Test audio was clean synthetic speech, not real recordings
- Status
- Not run
- Date
- October 21, 2026
- Time to first output
- —
- Cost
- —
- Result
- —
- Evidence
- Log linked below
Queued task. Render a fixed script in a chosen voice. Log time to the first usable take and artifacts.
FAQ
What is the agent-tested verdict for faster-whisper?
A free tool that turns speech into text. It's for people making images, video, or audio. It's free. We tried it ourselves. Grade A.
How much does faster-whisper cost?
Free. MIT.
Do sponsors outrank this tool?
No. A sponsored slot is labeled and sold separately from tiers. It cannot move this listing.