Grad-TTS

by Huawei Noah's Ark Lab

Diffusion-probabilistic TTS reference implementation.

Looking at Grad-TTS? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for researchers exploring diffusion-based TTS architectures. Pricing: free (MIT).

Category
Open source
License
—
Stars
★ 604
Last push
2023-09-18
Pricing
free (MIT)
Platforms
Linux

What it is

Grad-TTS is Huawei Noah's Ark Lab's diffusion-based TTS, one of the first applications of diffusion to speech synthesis. Demonstrates the lineage that StyleTTS 2 and F5-TTS extend. MIT. Consent posture: synthetic-only.

Best for: Researchers exploring diffusion-based TTS architectures.
Watch out for: Research-grade; sampling can be slow without distillation.

Install / use

git clone https://github.com/huawei-noah/Speech-Backbones

Features

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

Links

GitHub repo ↗

Grad-TTS vs Whipscribe

FeatureGrad-TTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (MIT)$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to Grad-TTS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.