Microsoft SpeechT5

by Microsoft

Unified speech-text Transformer (ASR + TTS + VC).

TL;DR

Unified speech-text Transformer (ASR + TTS + VC).

Best for researchers exploring unified speech-text pretraining. Pricing: free.

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

What it is

SpeechT5 unifies ASR, TTS, and voice conversion. MIT.

Best for: Researchers exploring unified speech-text pretraining.
Watch out for: English-only; small model zoo.

Install / use

git clone https://github.com/microsoft/SpeechT5

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

Microsoft SpeechT5 vs Whipscribe

FeatureMicrosoft SpeechT5Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to Microsoft SpeechT5

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.