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.
Conformer
ContextNet
ContextNet + Noisy Student
FastSpeech
🇺🇸 Zhejiang University (ZJU)
Transformer - LibriVox + Decoding/Rescoring
Big-Little Net (speech)
🇺🇸 IBM
Tacotron 2
DL scaling speech
🇨🇳 Baidu
Tacotron
MS-ensemble-speech-recognition
🇺🇸 Microsoft
WaveNet
🇺🇸 Google DeepMind
LF-MMI
🇺🇸 Johns Hopkins University
Segmental RNN
🇺🇸 University of Edinburgh
DeepSpeech2 (English)
🇺🇸 Baidu Research - Silicon Valley AI Lab
Listen, Attend and Spell
TC-DNN-BLSTM-DNN
🇺🇸 Carnegie Mellon University (CMU)
RNN-WER
🇬🇧 DeepMind
Clockwork RNN (CW-RNN)
🇨🇭 IDSIA
Multilingual DNN
ReLU-Speech
DistBelief Speech
KN5 LM + RNN 400/10 (WSJ)
🇺🇸 Brno University of Technology
RNN 1000/5 + RT09 LM (NIST RT05)
🇺🇸 Brno University of Technology
RNN 500/10 + RT09 LM (NIST RT05)
🇺🇸 Brno University of Technology
BP-DBN
🇺🇸 University of Toronto
BiLSTM for Speech
🇨🇭 IDSIA
Fuzzy NN
🇮🇳 Indian Statistical Institute
Weight Decay
Unknown
NETtalk reimplementation
🇺🇸 Oregon State University
Speaker-independent vowel classification
🇺🇸 University of Washington
Time-delay neural networks
🇺🇸 Advanced Telecommunications Research Institute
MLN-ASR
🇺🇸 McGill University
NetTalk (dictionary)
🇺🇸 Princeton University
NetTalk (transcription)
🇺🇸 Princeton University
PDP model for serial order
🇺🇸 University of California San Diego
Statistical continuous speech recognizer
🇺🇸 Massachusetts Institute of Technology (MIT)
LTE speaker verification system
🇺🇸 IBM
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.