Seamless (SeamlessM4T family)

by Meta AI

Meta's multilingual speech-translation + transcription foundation suite.

TL;DR

Meta's multilingual speech-translation + transcription foundation suite.

Best for open multilingual S2ST / S2TT research and 100+ language transcription. Pricing: free.

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

What it is

Includes SeamlessM4T v2, SeamlessExpressive, SeamlessStreaming, and the underlying w2v-BERT 2.0 encoder. Apache-2.0 code, CC-BY-NC weights.

Best for: Open multilingual S2ST / S2TT research and 100+ language transcription.
Watch out for: CC-BY-NC-4.0 — non-commercial; check Meta's model license before shipping.

Install / use

pip install fairseq2

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported101
HIPAA eligibleNo

Seamless (SeamlessM4T family) vs Whipscribe

FeatureSeamless (SeamlessM4T family)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages10199
PlatformsLinux, DockerWeb, API, MCP

Alternatives to Seamless (SeamlessM4T family)

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.