WhisperSpeech

by WhisperSpeech / Collabora

Whisper inverted into a TTS — also used as ASR-aware training data tool.

TL;DR

Whisper inverted into a TTS — also used as ASR-aware training data tool.

Best for researchers exploring speech-LM scaling laws built on Whisper embeddings. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux

What it is

An open speech-LM that re-uses Whisper's encoder as a semantic audio tokenizer. MIT.

Best for: Researchers exploring speech-LM scaling laws built on Whisper embeddings.
Watch out for: TTS-focused; not a transcription engine; checkpoints under MIT but evolving.

Install / use

git clone https://github.com/WhisperSpeech/WhisperSpeech

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

WhisperSpeech vs Whipscribe

FeatureWhisperSpeechWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinuxWeb, API, MCP

Alternatives to WhisperSpeech

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.