# faster-whisper v1.2.1: what's new, verdict & setup Canonical: https://theagenticweekly.com/tools/faster-whisper · Released: 2025-10-31 · Last verified: 2026-10-25 · Evidence: Tested (smoke test, 2026-10-25, no language model involved) · Vendor: SYSTRAN · Official site: https://github.com/SYSTRAN/faster-whisper > Speech-to-text library that runs OpenAI Whisper models with CTranslate2. ## Verdict **Fast local transcription; on CPU use float32 and check int8 against a reference before trusting it.** Good for: - Local, private transcription - Developers building voice pipelines on CPU Skip if: - You need diarisation or a managed service Tested. Tested 2026-10-25 (America/Chicago). faster-whisper 1.2.1 transcribed 41 s of speech at 2.4 percent word error with the base.en model in float32 (deterministic), but the int8 setting gave 2 to 60 percent on identical audio across runs. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. No language model was involved in this test, so it says nothing about any model, vendor-hosted or local. Not tested: Other audio: one synthetic (Piper) voice, English only, no noise, no accents, no long recordings; GPU, other compute types (float16, int8_float16) and the larger models; Not a benchmark; this is a smoke test on 41 seconds of audio. These are smoke tests, not a benchmark. Full log: /tests/faster-whisper. Test scope: - Kind and date: smoke test, 2026-10-25 (America/Chicago). Not a benchmark. - What we ran: faster-whisper 1.2.1 transcribed 41 s of speech at 2.4 percent word error with the base.en model in float32 (deterministic), but the int8 setting gave 2 to 60 percent on identical audio across runs. - Model used: None; no language model was involved - Environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key - Not tested: Other audio: one synthetic (Piper) voice, English only, no noise, no accents, no long recordings; GPU, other compute types (float16, int8_float16) and the larger models; Not a benchmark; this is a smoke test on 41 seconds of audio. Pricing: Partly verified. Open source; no pricing page read. (checked 2026-10-25) ## Best for - [Best AI tool for AI voice and speech](https://theagenticweekly.com/best/voice-ai) (#-): MIT-licensed Whisper inference library for CPU and GPU. ## Key facts faster-whisper reimplements Whisper inference with CTranslate2 for faster CPU and GPU transcription. It is MIT-licensed; v1.2.1 was tagged on 2025-10-31. - License: MIT (per GitHub) - Platforms: Python; CPU and NVIDIA GPU - Pricing model: Open source - Free tier: Open source, free to use - Paid plans: Hosted or enterprise offerings not read - GitHub: SYSTRAN/faster-whisper: 26,138 stars on 2026-10-25, last push 2026-10-25 - Latest release we saw: v1.2.1, 2025-10-31 - How to start: uv pip install faster-whisper av==18.1.0. - v1.2.1 (2025-10-31): the newest release on the repository when we read it on 2026-10-25. ## How to set it up: Get started with faster-whisper Install steps are exactly what we ran on 2026-10-25; the test log lists what was and was not covered. 1. **Install and pin av.** In our run an unpinned av release broke first use; pinning fixed it. ``` uv pip install faster-whisper av==18.1.0 ``` 2. **Transcribe.** Use float32 on CPU if you need repeatable output. ``` WhisperModel("base.en", device="cpu", compute_type="float32") ``` ## Pros and cons Pros: - MIT license - Repeatable word error rate in float32 on our test audio Cons: - int8 on CPU gave 2.4 to 59.7 percent word error on the same audio run to run in our test - An unpinned dependency (av 19.0.2) broke first use ## Alternatives - [Piper](https://theagenticweekly.com/tools/piper): Fast local neural text-to-speech that runs on CPU. - [Ollama](https://theagenticweekly.com/tools/ollama): The common way to run open models locally on macOS, Windows and Linux, with a cloud option and an MIT-licensed open-source core. - [llama.cpp](https://theagenticweekly.com/tools/llama-cpp): LLM inference in C/C++: the open-source engine many local-model tools build on; MIT-licensed with near-daily build tags. - [AssemblyAI](https://theagenticweekly.com/tools/assemblyai): Speech AI APIs for transcription and understanding; start free, pay as you go. - [Cartesia](https://theagenticweekly.com/tools/cartesia): Realtime voice AI: text-to-speech, speech-to-text in 44 languages and voice agents, with a free plan and credit tiers. - [Deepgram](https://theagenticweekly.com/tools/deepgram): Voice AI APIs for speech-to-text, text-to-speech and agents with $200 in free credit. - [Murf AI](https://theagenticweekly.com/tools/murf-ai): Text-to-speech platform with a $10 free API trial, pay-as-you-go credits and per-character API pricing. - [Resemble AI](https://theagenticweekly.com/tools/resemble-ai): Resemble AI now leads with real-time deepfake detection and watermarking for audio, video and images; plans from free to $1,000 a month. - [Retell AI](https://theagenticweekly.com/tools/retell): Voice AI agents for phone calls with pay-per-minute pricing and 20 free concurrent calls. - [Speechify](https://theagenticweekly.com/tools/speechify): Text-to-speech app that reads PDFs, books and web pages aloud, with a Free plan and a $29 monthly premium price. - [Vapi](https://theagenticweekly.com/tools/vapi): Developer platform for voice agents; $5 free credits, then pay for the minutes you run. ## FAQ ### What is faster-whisper? A library that runs Whisper speech-to-text models with CTranslate2 for faster inference. ### Is int8 safe on CPU? Check it first: in our test the same audio gave between 2.4 and 59.7 percent word error across int8 runs, while float32 was stable. See /tests/faster-whisper. ### Why did faster-whisper fail on first use? An unpinned av 19.0.2 raised a TypeError in our run; av==18.1.0 fixed it. ## What we have not verified - GPU speed - Non-English audio, noisy audio, long recordings ## Sources - [faster-whisper repository (GitHub)](https://github.com/SYSTRAN/faster-whisper) (fetched 2026-10-25) ## How to cite Agentic Weekly, "faster-whisper v1.2.1: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/faster-whisper Keep the Reported or Tested label when you quote the verdict.