Best Open-Source Speech-to-text options.
Candidates with open-source, open-weight, downloadable pretrained, or self-hosted signals from source metadata. Automated radar ranking for ASR, transcription, diarization, and real-time speech-to-text models and APIs. Rankings use existing source-backed radar data and do not invent prices, benchmark scores, release dates, or capabilities.
NVIDIA Riva
Highest automated fit score using source-backed task evidence and radar signals.
NVIDIA Riva
Strong candidate when the source metadata indicates API or hosted-service availability.
NVIDIA Riva
Strong candidate when open weights, GitHub, permissive license, or self-hosting signals are visible.
screenpipe/screenpipe
Strong candidate with fresh GitHub, Hub, Product Hunt, or radar momentum.
| # | Candidate | Type | Access | Source | Fit | Updated | Why it matched | Evidence |
|---|---|---|---|---|---|---|---|---|
| 01 | NVIDIA RivaNVIDIA API service | service | Paid API | Official service page | Score81 | Jun 26, 2026 | Matched speech-to-text, speech to text, asr; 2 source links; official service signal; access model: Paid API | developer.nvidia.com |
| 02 | NVIDIA NIM Model CatalogNVIDIA inference platform | service | Free endpoint | Official inference catalog | Score75 | Jun 26, 2026 | Matched speech-to-text, speech to text; 3 source links; official inference catalog signal; access model: Free endpoint | build.nvidia.com |
| 03 | screenpipe/screenpipeRust repository | repo | Open source | GitHub | Score68 | Oct 3, 2026 | Matched speech-to-text, speech to text; 1 source link; access model: Open source; freshly updated | github.com |
| 04 | gojargo/jargoGo repository | repo | Open source | GitHub | Score67 | Jul 20, 2026 | Matched speech-to-text, speech to text, stt; 1 source link; access model: Open source; open weights signal | github.com |
| 05 | Osmantic/ODSPython repository | repo | Open source | GitHub | Score63 | Jul 28, 2026 | Matched speech-to-text, speech to text; 1 source link; access model: Open source; open weights signal | github.com |
| 06 | ragibhasan/bangla_speech_corpus_v1ragibhasan model | model | Open weights | Hugging Face Models | Score62 | Sep 30, 2026 | Matched automatic speech recognition, speech recognition; 2 source links; access model: Open weights; freshly updated | huggingface.co |
| 07 | AuraVixStudio/caeloPython repository | repo | Open source | GitHub | Score58 | Jul 8, 2026 | Matched speech-to-text, speech to text; 1 source link; access model: Open source; open weights signal | github.com |
Track Speech-to-text changes
The model, API, pricing and tooling changes that matter, in one morning email with links to the original sources. Free, unsubscribe in one click.
Prefer topic alerts or a custom RSS feed?