owenawsong / Inflect
Inflect v3: compact local text-to-speech. Six English voices, three model sizes, reference-voice tuning, event tags and optional 48 kHz output. Apache 2.0.
Why this job: says: text to speech; topics: text-to-speech, tts
What it does
Six English voices. Three model sizes. Speech that runs on your hardware.
Get started
python -m pip install -r core/requirements-cuda.txt
python run.py speech --device cuda --runtime cuda-source --profile base --voice cassidy --text "A small idea can become something worth hearing." --subtype PCM_16 --output ../mini-cuda.wav - Maintenance
- Active
- Last commit today
- Stars
- 168
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 8 merged
- 0 waiting
- Releases
- None
- Never published
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| leemysw / yovoice | 2,167 | yesterday | Apache-2.0 | Mac, Windows, Linux |
| OpenMOSS / MOSS-TTS | 4,321 | 2 months ago | Apache-2.0 | No downloads |
| kadirnar / voicehub | 121 | 39 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- PowerShell <1%
- Shell <1%
Topics
- audio
- inflect
- tts
- voice
- text-to-speech
Project record
- JobSpeech and audio
- StatusListed
- Commits45
- Forks15
- Watching4
- Stars in 28 days+7
- CreatedApr 4, 2026
- First seen by usNov 12, 2026
- CheckedNov 12, 2026