New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Speech AI models
Browse the complete list of Speech AI models. Compare specifications, benchmark scores and provider pricing on GenAIList.
Cartesia Ink-2
🇺🇸 Cartesia
Sonic-3.5
🇺🇸 Cartesia
Chatterbox Multilingual v3
🇺🇸 Resemble AI
Gemini 3.5 Live Translate
🇺🇸 Google DeepMind
Higgs Audio v3 TTS
Boson AI
NVIDIA Nemotron 3.5 ASR Streaming 0.6B
🇺🇸 NVIDIA
NeuTTS Nano
Neuphonic
MAI-Transcribe-1.5
🇺🇸 Microsoft
MAI-Voice-2
🇺🇸 Microsoft
Microsoft MAI-Voice-2-Flash
🇺🇸 Microsoft
Dubbing v2
🇺🇸 ElevenLabs
Rime Coda
Rime
StepAudio 2.5 Realtime
🇨🇳 StepFun
Hunyuan Voice
🇨🇳 Tencent Hunyuan
Qwen3.5-LiveTranslate-Flash
🇨🇳 Qwen
GPT-Realtime-Translate
🇺🇸 OpenAI
GPT-Realtime-Whisper
🇺🇸 OpenAI
Inworld Realtime TTS-2
Inworld AI
Deepgram Flux Multilingual
🇺🇸 Deepgram
Step-Audio-R1.5
🇨🇳 StepFun
Grok Voice Think Fast 1.0
🇺🇸 xAI
Qwen3-TTS
🇨🇳 Alibaba
Grok Voice Agent API
🇺🇸 xAI
Amazon Nova 2 Sonic
🇺🇸 Amazon
Velvet Speech 2B
🇮🇹 Almawave
EVI 4 mini
🇺🇸 Hume
Octave 2
🇺🇸 Hume
Chatterbox Multilingual
🇺🇸 Resemble AI
MAI-Voice-1
🇺🇸 Microsoft
gpt-realtime
🇺🇸 OpenAI
Sibilia-TTS
🇮🇹 DeepMount00
Canary 1B v2
🇺🇸 NVIDIA
Parakeet-tdt-0.6b-v3
🇺🇸 NVIDIA
Voxtral Mini
🇫🇷 Mistral AI
Voxtral Small
🇫🇷 Mistral AI
Voxtral Mini Transcribe
🇫🇷 Mistral AI
Ink Whisper
🇺🇸 Cartesia
Eleven v3
🇺🇸 ElevenLabs
Gemini 2.5 Flash Native Audio
🇺🇸 Google DeepMind
OpenAudio-S1
🇺🇸 Fish Audio
OpenAudio-S1-mini
🇺🇸 Fish Audio
FAMA Medium
🇮🇹 Fondazione Bruno Kessler
EVI 3
🇺🇸 Hume
Minimax-Speech-02-HD
🇨🇳 MiniMax
MiniMax-Speech-02-turbo
🇨🇳 MiniMax
Nova-3
🇺🇸 Deepgram
Amazon Nova Sonic
🇺🇸 Amazon
Papla P1
Papla Media
Chirp 3 HD Text-to-Speech
Chirp 3 Speech-to-Text
YuE
🇺🇸 Hong Kong University of Science and Technology (HKUST)
Sonic 2
🇺🇸 Cartesia
Eleven Scribe
🇺🇸 ElevenLabs
Step-Audio-Chat 130B
🇨🇳 StepFun
Step-Omni
🇨🇳 StepFun
Step-Audio-TTS-3B
🇨🇳 StepFun
Zonos-v0.1
🇺🇸 Zyphra
Kokoro v1.0
hexgrad
MiniMax Speech-01-turbo (T2A-01-turbo)
🇨🇳 MiniMax
MiniMax Speech-01-HD (T2A-01-HD)
🇨🇳 MiniMax
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.