// MODEL CATEGORY

Speech AI models

Browse the complete list of Speech AI models. Compare specifications, benchmark scores and provider pricing on GenAIList.

157 models
VO

Voiseed Xpressive

๐Ÿ‡ฎ๐Ÿ‡น Voiseed

Jan 2025
Speech Proprietary
HE

Kokoro v0.19

hexgrad

Dec 2024 82M
Speech Open (Restricted)
HU

OCTAVE 3B

๐Ÿ‡บ๐Ÿ‡ธ Hume

Dec 2024 3B
Speech Proprietary
HU

OCTAVE 8B

๐Ÿ‡บ๐Ÿ‡ธ Hume

Dec 2024 8B
Speech Proprietary
ElevenLabs

Eleven Flash v2.5

๐Ÿ‡บ๐Ÿ‡ธ ElevenLabs

Dec 2024
Speech Proprietary
SJ

F5-TTS

๐Ÿ‡บ๐Ÿ‡ธ Shanghai Jiao Tong University

Dec 2024 335.8M
Speech Open Weights
FA

Fish-Speech 1.5

๐Ÿ‡บ๐Ÿ‡ธ Fish Audio

Nov 2024
Speech Open Weights
FA

Fish-Speech 1.4

๐Ÿ‡บ๐Ÿ‡ธ Fish Audio

Nov 2024
Speech Open Weights
AS

Universal-2-TF

๐Ÿ‡บ๐Ÿ‡ธ AssemblyAI

Oct 2024 600M
Speech Proprietary
Cartesia

Sonic

๐Ÿ‡บ๐Ÿ‡ธ Cartesia

Oct 2024
Speech Proprietary
KH

Belle-whisper-larger-v3-turbo-zh

๐Ÿ‡จ๐Ÿ‡ณ KE Holdings Inc. (โ€œBeikeโ€)

Oct 2024
Speech Open (Restricted)
GO

Chirp 2 Speech-to-Text

๐Ÿ‡บ๐Ÿ‡ธ Google

Oct 2024
Speech Proprietary
Microsoft

E2 TTS

๐Ÿ‡บ๐Ÿ‡ธ Microsoft

Sep 2024 335M
Speech Proprietary
HU

EVI 2

๐Ÿ‡บ๐Ÿ‡ธ Hume

Sep 2024
Speech Proprietary
WL

Xinchen Lingo

๐Ÿ‡จ๐Ÿ‡ณ West Lake Xinchen / Xinchen AI / ่ฅฟๆน–ๅฟƒ่พฐ๏ผˆๆญๅทž๏ผ‰็ง‘ๆŠ€ๆœ‰้™ๅ…ฌๅธ

Sep 2024
Speech Proprietary
SA

Shuka-1

๐Ÿ‡ฎ๐Ÿ‡ณ Sarvam

Aug 2024 9.6B
Speech Open (Restricted)
SA

Saaras v1

๐Ÿ‡ฎ๐Ÿ‡ณ Sarvam

Aug 2024 1.5B
Speech Proprietary
AI

OuteTTS-0.1-350M

Unknown

Aug 2024 350M
Speech Open (Restricted)
MT

MooER

๐Ÿ‡จ๐Ÿ‡ณ Moore Threads

Aug 2024 7.2B
Speech Proprietary
AG

BaiLing TTS

๐Ÿ‡จ๐Ÿ‡ณ Ant Group

Aug 2024
Speech Proprietary
ElevenLabs

Eleven Turbo v2.5

๐Ÿ‡บ๐Ÿ‡ธ ElevenLabs

Jul 2024
Speech Proprietary
SO

YiYuan (ๅฃนๅ…ƒๅคงๆจกๅž‹)

๐Ÿ‡จ๐Ÿ‡ณ SoundAI

Jul 2024
Speech Proprietary
TR

Matedub

๐Ÿ‡ฎ๐Ÿ‡น Translated

Jun 2024
Speech Proprietary
CT

Xingchen Voice Model (ๆ˜Ÿ่พฐ่ฏญ้Ÿณๅคงๆจกๅž‹)

๐Ÿ‡จ๐Ÿ‡ณ China Telecom

Jun 2024 300M
Speech Open (Restricted)
ByteDance

Doubao Speech Recognition Model

๐Ÿ‡จ๐Ÿ‡ณ ByteDance

May 2024
Speech Proprietary
ByteDance

Doubao Text-to-Speech Model

๐Ÿ‡จ๐Ÿ‡ณ ByteDance

May 2024
Speech Proprietary
ByteDance

Doubao Voice Cloning Model

๐Ÿ‡จ๐Ÿ‡ณ ByteDance

May 2024
Speech Proprietary
AI

SeedLLM

Unknown

Apr 2024 7B
Speech Proprietary
HU

EVI

๐Ÿ‡บ๐Ÿ‡ธ Hume

Apr 2024
Speech Proprietary
NVIDIA

Parakeet ASR rnnt 1.1B

๐Ÿ‡บ๐Ÿ‡ธ NVIDIA

Apr 2024 1.1B
Speech Open (Restricted)
AS

Universal-1

๐Ÿ‡บ๐Ÿ‡ธ AssemblyAI

Apr 2024 600M
Speech Proprietary
GA

HAM-TTS

๐Ÿ‡จ๐Ÿ‡ณ Geely Automobile Research Institute (Ningbo) Company

Mar 2024 800M
Speech Proprietary
FA

SeamlessM4T

๐Ÿ‡บ๐Ÿ‡ธ Facebook

Dec 2023 2.3B
Speech Open (Restricted)
SO

AzeroGPT

๐Ÿ‡จ๐Ÿ‡ณ SoundAI

Dec 2023 100B
Speech Proprietary
CM

Mamba-24M (SC09)

๐Ÿ‡บ๐Ÿ‡ธ Carnegie Mellon University (CMU)

Dec 2023 23.4M
Speech Proprietary
AM

Amazon Transcribe

๐Ÿ‡บ๐Ÿ‡ธ Amazon

Nov 2023
Speech Proprietary
CU

StyleTTS 2

๐Ÿ‡บ๐Ÿ‡ธ Columbia University

Nov 2023
Speech Open (Restricted)
OpenAI

tts-1

๐Ÿ‡บ๐Ÿ‡ธ OpenAI

Nov 2023
Speech Proprietary
OpenAI

tts-1-hd

๐Ÿ‡บ๐Ÿ‡ธ OpenAI

Nov 2023
Speech Proprietary
OpenAI

Whisper v3

๐Ÿ‡บ๐Ÿ‡ธ OpenAI

Nov 2023 1.6B
Speech Open (Restricted)
FA

Voicebox / VB-En

๐Ÿ‡บ๐Ÿ‡ธ Facebook AI Research

Oct 2023 358M
Speech Proprietary
DE

Nova-2

๐Ÿ‡บ๐Ÿ‡ธ Deepgram

Sep 2023
Speech Proprietary
ElevenLabs

Eleven Multilingual v2

๐Ÿ‡บ๐Ÿ‡ธ ElevenLabs

Aug 2023
Speech Proprietary
GO

Chirp

๐Ÿ‡บ๐Ÿ‡ธ Google

Jun 2023 2B
Speech Proprietary
MA

MMS-1B

๐Ÿ‡บ๐Ÿ‡ธ Meta AI

May 2023 1B
Speech Open Weights
ElevenLabs

Eleven Multilingual v1

๐Ÿ‡บ๐Ÿ‡ธ ElevenLabs

Apr 2023
Speech Proprietary
Microsoft

VALL-E X

๐Ÿ‡บ๐Ÿ‡ธ Microsoft

Mar 2023 700M
Speech Proprietary
ElevenLabs

Eleven Monolingual v1

๐Ÿ‡บ๐Ÿ‡ธ ElevenLabs

Jan 2023
Speech Proprietary
OpenAI

Whisper v2

๐Ÿ‡บ๐Ÿ‡ธ OpenAI

Dec 2022 1.6B
Speech Open (Restricted)
OpenAI

Whisper

๐Ÿ‡บ๐Ÿ‡ธ OpenAI

Sep 2022 1.6B
Speech Open (Restricted)
SD

SauTech

๐Ÿ‡ธ๐Ÿ‡ฆ Saudi Data and Artificial Intelligence Authority

Sep 2022
Speech Proprietary
ZU

FastSpeech 2

๐Ÿ‡บ๐Ÿ‡ธ Zhejiang University (ZJU)

Aug 2022 27M
Speech Proprietary
NVIDIA

STT Conformer-Transducer XL

๐Ÿ‡บ๐Ÿ‡ธ NVIDIA

Apr 2022 600M
Speech Open (Restricted)
SP

Speechmatics Enhanced

๐Ÿ‡ฌ๐Ÿ‡ง Speechmatics

Sep 2021
Speech Proprietary
SP

Speechmatics Standard

๐Ÿ‡ฌ๐Ÿ‡ง Speechmatics

Aug 2021
Speech Proprietary
GB

W2v-BERT

๐Ÿ‡บ๐Ÿ‡ธ Google Brain

Aug 2021 1B
Speech Proprietary
FA

HuBERT

๐Ÿ‡บ๐Ÿ‡ธ Facebook AI Research

Jul 2021 1B
Speech Open (Restricted)
UO

top-down frozen classifier

๐Ÿ‡บ๐Ÿ‡ธ University of Edinburgh

Feb 2021
Speech Proprietary
FA

wave2vec 2.0 LARGE

๐Ÿ‡บ๐Ÿ‡ธ Facebook

Oct 2020 317M
Speech Open (Restricted)
GO

Conformer + Wav2vec 2.0 + Noisy Student

๐Ÿ‡บ๐Ÿ‡ธ Google

Oct 2020 1B
Speech Proprietary

About Speech AI models

This page lists every Speech AI models tracked on GenAIList. When choosing a model, weigh raw capability against practical constraints like context window, latency, licensing and price. Open-weights and open-source models can be self-hosted and fine-tuned, while proprietary models often lead on raw quality. Compare benchmark scores on our benchmarks page and put two candidates head to head with compare.

Frequently asked questions

How do I choose the right model?

Weigh raw capability against practical constraints like context window, latency, licensing and price. Use the benchmarks page to compare rankings and the compare tool to evaluate two candidates side by side.

Where can I see benchmark scores?

Visit the benchmarks page to compare these models on standardised tests, then use the compare tool for a detailed side-by-side of any two models.