All categories
14 entries
Voice: speech-to-text & TTS
Talk to it and hear it answer, offline.
Where this sits
- Modelthe weights
- Runtimeruns & routes it
- Harnessmakes it act
- Memorymakes it remember
- Voice:Toolsgives it hands
Runbook
whisper.cpp
Speech-to-text that runs on your machine.
54K
Whisper
OpenAI's original speech recognition model.
111K
ChatTTS
Conversational text-to-speech model.
40K
Handy
Offline push-to-talk dictation app.
34K
Fish Speech
Open-source text-to-speech with voice cloning.
33K
Chatterbox
Open-source expressive TTS.
27K
faster-whisper
Whisper transcription, faster, via CTranslate2.
26K
WhisperX
Whisper with word timestamps and speaker labels.
25K
CosyVoice
Multilingual voice generation model.
24K
Dia
TTS that generates realistic dialogue.
19K
NeMo (Parakeet)
NVIDIA NeMo speech models (incl. Parakeet).
19K
MLX-Audio
TTS, STT and speech-to-speech on MLX.
Apple Silicon8K
WhisperKit
On-device speech AI for Apple Silicon (WhisperKit).
Apple Silicon6.4K
Parakeet MLX
NVIDIA Parakeet speech recognition on MLX.
Apple Silicon987
# Voice: speech-to-text & TTS (14) Talk to it and hear it answer, offline. | slug | name | tier | stars | what | md | |---|---|---|---|---|---| | whisper-cpp | whisper.cpp | runbook | 54418 | Speech-to-text that runs on your machine. | /setups/whisper-cpp.md | | whisper | Whisper | catalog | 110561 | OpenAI's original speech recognition model. | /setups/whisper.md | | chattts | ChatTTS | catalog | 39909 | Conversational text-to-speech model. | /setups/chattts.md | | handy | Handy | catalog | 33870 | Offline push-to-talk dictation app. | /setups/handy.md | | fish-speech | Fish Speech | catalog | 33167 | Open-source text-to-speech with voice cloning. | /setups/fish-speech.md | | chatterbox | Chatterbox | catalog | 26965 | Open-source expressive TTS. | /setups/chatterbox.md | | faster-whisper | faster-whisper | catalog | 25876 | Whisper transcription, faster, via CTranslate2. | /setups/faster-whisper.md | | whisperx | WhisperX | catalog | 24579 | Whisper with word timestamps and speaker labels. | /setups/whisperx.md | | cosyvoice | CosyVoice | catalog | 23997 | Multilingual voice generation model. | /setups/cosyvoice.md | | dia | Dia | catalog | 19407 | TTS that generates realistic dialogue. | /setups/dia.md | | nemo-parakeet | NeMo (Parakeet) | catalog | 18585 | NVIDIA NeMo speech models (incl. Parakeet). | /setups/nemo-parakeet.md | | mlx-audio | MLX-Audio | catalog | 8049 | TTS, STT and speech-to-speech on MLX. | /setups/mlx-audio.md | | whisperkit | WhisperKit | catalog | 6404 | On-device speech AI for Apple Silicon (WhisperKit). | /setups/whisperkit.md | | parakeet-mlx | Parakeet MLX | catalog | 987 | NVIDIA Parakeet speech recognition on MLX. | /setups/parakeet-mlx.md |