whisper.cpp alternatives.
whisper.cpp: Speech-to-text that runs on your machine. Here are other voice: speech-to-text & tts tools, most-starred first.
| Tool | What it does | Licence | GitHub stars |
|---|---|---|---|
| Whisper | OpenAI's original speech recognition model. | MIT | 110,561 |
| ChatTTS | Conversational text-to-speech model. | AGPL-3.0 | 39,909 |
| Handy | Offline push-to-talk dictation app. | MIT | 33,870 |
| Fish Speech | Open-source text-to-speech with voice cloning. | Other | 33,167 |
| Chatterbox | Open-source expressive TTS. | MIT | 26,965 |
| faster-whisper | Whisper transcription, faster, via CTranslate2. | MIT | 25,876 |
| WhisperX | Whisper with word timestamps and speaker labels. | BSD-2-Clause | 24,579 |
| CosyVoice | Multilingual voice generation model. | Apache-2.0 | 23,997 |
| Dia | TTS that generates realistic dialogue. | Apache-2.0 | 19,407 |
| NeMo (Parakeet) | NVIDIA NeMo speech models (incl. Parakeet). | Apache-2.0 | 18,585 |
| MLX-Audio | TTS, STT and speech-to-speech on MLX. | MIT | 8,049 |
| WhisperKit | On-device speech AI for Apple Silicon (WhisperKit). | MIT | 6,404 |
Stars are a popularity signal, not a quality score. Gap Scores come after our Mac Studio tests.
# whisper.cpp alternatives URL: https://insidethemachine.ai/alternatives/whisper-cpp whisper.cpp: Speech-to-text that runs on your machine. Talk to your agent, offline and private. Category: Voice: speech-to-text & TTS. Sorted by GitHub stars (checked 2026-10-15). | name | what | licence | stars | md | |---|---|---|---|---| | Whisper | OpenAI's original speech recognition model. | MIT | 110561 | https://insidethemachine.ai/setups/whisper.md | | ChatTTS | Conversational text-to-speech model. | AGPL-3.0 | 39909 | https://insidethemachine.ai/setups/chattts.md | | Handy | Offline push-to-talk dictation app. | MIT | 33870 | https://insidethemachine.ai/setups/handy.md | | Fish Speech | Open-source text-to-speech with voice cloning. | Other | 33167 | https://insidethemachine.ai/setups/fish-speech.md | | Chatterbox | Open-source expressive TTS. | MIT | 26965 | https://insidethemachine.ai/setups/chatterbox.md | | faster-whisper | Whisper transcription, faster, via CTranslate2. | MIT | 25876 | https://insidethemachine.ai/setups/faster-whisper.md | | WhisperX | Whisper with word timestamps and speaker labels. | BSD-2-Clause | 24579 | https://insidethemachine.ai/setups/whisperx.md | | CosyVoice | Multilingual voice generation model. | Apache-2.0 | 23997 | https://insidethemachine.ai/setups/cosyvoice.md | | Dia | TTS that generates realistic dialogue. | Apache-2.0 | 19407 | https://insidethemachine.ai/setups/dia.md | | NeMo (Parakeet) | NVIDIA NeMo speech models (incl. Parakeet). | Apache-2.0 | 18585 | https://insidethemachine.ai/setups/nemo-parakeet.md | | MLX-Audio | TTS, STT and speech-to-speech on MLX. | MIT | 8049 | https://insidethemachine.ai/setups/mlx-audio.md | | WhisperKit | On-device speech AI for Apple Silicon (WhisperKit). | MIT | 6404 | https://insidethemachine.ai/setups/whisperkit.md |