SSyncDev

Text-to-speech AI Models

Models listed

88

Published in this category

Worth weighing up

What goes in and out, licence terms, and whether you can host it yourself

How we treat data

Published specs only — we don't estimate numbers a vendor hasn't stated

Text-to-speech models are a source-backed task collection in this directory. The current editorial inventory contains 33 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.

Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.

This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.

Text-to-speech model list

Scan the table below, then open any model for pricing, limits and the full write-up.

88 models
Qwen-Audio-3.1-TTS Next
Alibaba
14.9————
Qwen-Audio-3.1-TTS Plus
Alibaba
9.8————
Voxtral TTS 3
Mistral AI
9.8————
Ming-3.0-tts-0.5B
inclusionAI
14.8————
Qwen-Audio-3.1-TTS Flash
Alibaba
9.8————
MAI-Voice-2.1
Microsoft
—————
MAI-Voice-2.1-Flash
Microsoft
—————
Gemini 3.8 Flash TTS
Google
17.98.19K———
Gemini 3.8 Flash-Lite TTS
Google
17.98.19K———
Grok Voice TTS 1.0
xAI
—15K———
GPT-Realtime-2.1
OpenAI
67.6128K$4.00$24.00—
Gemini 3.5 Live Translate Preview
Google
39.1131.07K$3.50$21.00—
Gemini 3.1 Flash Live Preview
Google
73.7131.07K$0.75$4.50—
Lyria 3 Clip Preview
Google
38.7131.07K$0.00$0.00—
Lyria 3 Pro Preview
Google
34.2131.07K$0.00$0.00—
MiMo-V2-TTS
Xiaomi
15.28.19K———
Seedance 2.0 Fast
ByteDance Seed
28.5————
Qwen-Omni Turbo
Alibaba
42.132.77K$0.07$0.27—
Ming Flash Omni 2.0
inclusionAI
20.0————
StepAudio 3 Gen Preview
StepFun
10.0————
MiniMax Speech 2.8 HD
MiniMax
5.0————
MiniMax Speech 2.8 TURBO
MiniMax
5.0————
StepAudio 3 TTS
StepFun
5.0————
ZONOS3-Mini
zyphra
25.132.77K———
Bulbul V4 Flash
Sarvam
9.8————
Drama 3
fish-audio
9.8————
HeyGen Voice
heygen
9.8————
HeyGen Voice Turbo
heygen
9.8————
Eleven v4
ElevenLabs
9.7—$80.00——
Eleven v4 Turbo
ElevenLabs
9.7—$40.00——
Chatterbox Nano
resemble-ai
8.8————
LFM3-Audio-2B
Liquid AI
35.032.77K———
LongCat Next
Meituan LongCat
31.8131.07K———
Qwen3.8 Omni Flash Realtime
Qwen
25.0————
ai4bharat/indic-parler-tts
ai4bharat
5.0————
audio-cpp/audio.cpp-gguf
audio-cpp
5.0————
bosonai/higgs-tts-2-3b-base
bosonai
5.0————
bosonai/higgs-tts-3-4b
bosonai
5.0————
coqui/XTTS-v2
coqui
5.0————
drbaph/Higgs-Audio-v3-Studio
drbaph
5.0————
facebook/hf-seamless-m4t-medium
facebook
5.0————
facebook/mms-tts-bam
facebook
5.0————
facebook/mms-tts-bod
facebook
5.0————
facebook/mms-tts-eng
facebook
5.0————
fishaudio/s2-pro
fishaudio
5.0————
hexgrad/Kokoro-82M
hexgrad
5.0————
k2-fsa/OmniVoice
k2-fsa
5.0————
kenpath/svara-tts-v1
kenpath
5.0————
kyutai/tts-1.6b-en_fr
kyutai
5.0————
microsoft/speecht5_tts
Microsoft Research
5.0————
microsoft/VibeVoice-1.5B
Microsoft Research
5.0————
microsoft/VibeVoice-Realtime-0.5B
Microsoft Research
5.0————
Misha24-10/F5-TTS_RUSSIAN
Misha24-10
5.0————
moonshotai/Kimi-Audio-7B-Instruct
moonshotai
5.0————
myshell-ai/MeloTTS-English
myshell-ai
5.0————
myshell-ai/MeloTTS-Korean
myshell-ai
5.0————
myshell-ai/MeloTTS-Spanish
myshell-ai
5.0————
notmax123/Zonos-Hebrew
notmax123
5.0————
onnx-community/Kokoro-82M-ONNX
onnx-community
5.0————
onnx-community/Kokoro-82M-v1.0-ONNX
onnx-community
5.0————

1–60 of 88 models · select a column to sort

About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

Text-to-speech model questions

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.

All AI models →