{"title": "Speech-to-text SDK and library downloads on PyPI and npm, tracked", "pillar": "speech-recognition", "api": {"name": "pypistats.org API and npm downloads API", "docs": "https://pypistats.org/api/"}, "cadence": "weekly", "sets": ["stt-package-downloads"], "method": "Once a week we read the last month's downloads of every Python package (from pypistats.org, which counts PyPI's public download logs without mirrors) and npm package (from npm's public downloads API) that our market registry lists for a speech-to-text API or open model.", "context": "A download is one install of the package, by a developer's machine or, far more often, by an automated build. The count is a measure of how much software is built on a provider, not of people.", "caveats": "Continuous-integration systems that install packages on every build dominate the counts, and one large customer can move them. Installs from private mirrors and caches are not counted.", "run": "packages", "kind": "tracked", "date": "2026-10-19", "runs": [{"date": "2026-10-19", "started": "2026-10-19T11:31:01Z", "finished": "2026-10-19T11:38:57Z", "requests": 100, "answered": 98, "failed": 0, "observations": 98, "archive": "packages/2026-10-19.jsonl.gz", "sha256": "ed7588bde0237664d62e335127d65ca296b453bd87b726d6e6a6d7963785abe5"}], "series": {"stt-package-downloads": {"pypi-dashscope": {"entity": "alibaba-cloud-speech-recognition", "label": "dashscope (PyPI)", "dims": {"package": "dashscope", "ecosystem": "PyPI", "project": "Alibaba Cloud Model Studio speech recognition", "segment": "Speech-to-text API", "maker": "Alibaba Cloud"}, "obs": [["2026-10-19", 2487885]]}, "pypi-amazon-transcribe": {"entity": "amazon-transcribe", "label": "amazon-transcribe (PyPI)", "dims": {"package": "amazon-transcribe", "ecosystem": "PyPI", "project": "Amazon Transcribe", "segment": "Speech-to-text API", "maker": "Amazon Web Services"}, "obs": [["2026-10-19", 734003]]}, "npm-aws-sdk-client-transcribe": {"entity": "amazon-transcribe", "label": "@aws-sdk/client-transcribe (npm)", "dims": {"package": "@aws-sdk/client-transcribe", "ecosystem": "npm", "project": "Amazon Transcribe", "segment": "Speech-to-text API", "maker": "Amazon Web Services"}, "obs": [["2026-10-19", 2186454]]}, "npm-aws-sdk-client-transcribe-streaming": {"entity": "amazon-transcribe", "label": "@aws-sdk/client-transcribe-streaming (npm)", "dims": {"package": "@aws-sdk/client-transcribe-streaming", "ecosystem": "npm", "project": "Amazon Transcribe", "segment": "Speech-to-text API", "maker": "Amazon Web Services"}, "obs": [["2026-10-19", 1277058]]}, "pypi-assemblyai": {"entity": "assemblyai", "label": "assemblyai (PyPI)", "dims": {"package": "assemblyai", "ecosystem": "PyPI", "project": "AssemblyAI", "segment": "Speech-to-text API", "maker": "AssemblyAI"}, "obs": [["2026-10-19", 2797588]]}, "npm-assemblyai": {"entity": "assemblyai", "label": "assemblyai (npm)", "dims": {"package": "assemblyai", "ecosystem": "npm", "project": "AssemblyAI", "segment": "Speech-to-text API", "maker": "AssemblyAI"}, "obs": [["2026-10-19", 2280177]]}, "pypi-azure-cognitiveservices-speech": {"entity": "azure-ai-speech", "label": "azure-cognitiveservices-speech (PyPI)", "dims": {"package": "azure-cognitiveservices-speech", "ecosystem": "PyPI", "project": "Azure AI Speech", "segment": "Speech-to-text API", "maker": "Microsoft"}, "obs": [["2026-10-19", 2520663]]}, "npm-microsoft-cognitiveservices-speech-sdk": {"entity": "azure-ai-speech", "label": "microsoft-cognitiveservices-speech-sdk (npm)", "dims": {"package": "microsoft-cognitiveservices-speech-sdk", "ecosystem": "npm", "project": "Azure AI Speech", "segment": "Speech-to-text API", "maker": "Microsoft"}, "obs": [["2026-10-19", 1875468]]}, "npm-azure-ai-speech-transcription": {"entity": "azure-ai-speech", "label": "@azure/ai-speech-transcription (npm)", "dims": {"package": "@azure/ai-speech-transcription", "ecosystem": "npm", "project": "Azure AI Speech", "segment": "Speech-to-text API", "maker": "Microsoft"}, "obs": [["2026-10-19", 7713]]}, "pypi-baidu-aip": {"entity": "baidu-speech-recognition", "label": "baidu-aip (PyPI)", "dims": {"package": "baidu-aip", "ecosystem": "PyPI", "project": "Baidu Speech Recognition", "segment": "Speech-to-text API", "maker": "Baidu"}, "obs": [["2026-10-19", 38841]]}, "npm-baidu-aip-sdk": {"entity": "baidu-speech-recognition", "label": "baidu-aip-sdk (npm)", "dims": {"package": "baidu-aip-sdk", "ecosystem": "npm", "project": "Baidu Speech Recognition", "segment": "Speech-to-text API", "maker": "Baidu"}, "obs": [["2026-10-19", 6135]]}, "pypi-cartesia": {"entity": "cartesia-ink", "label": "cartesia (PyPI)", "dims": {"package": "cartesia", "ecosystem": "PyPI", "project": "Cartesia Ink", "segment": "Speech-to-text API", "maker": "Cartesia"}, "obs": [["2026-10-19", 707919]]}, "npm-cartesia-cartesia-js": {"entity": "cartesia-ink", "label": "@cartesia/cartesia-js (npm)", "dims": {"package": "@cartesia/cartesia-js", "ecosystem": "npm", "project": "Cartesia Ink", "segment": "Speech-to-text API", "maker": "Cartesia"}, "obs": [["2026-10-19", 459483]]}, "pypi-cloudflare": {"entity": "cloudflare-workers-ai-whisper", "label": "cloudflare (PyPI)", "dims": {"package": "cloudflare", "ecosystem": "PyPI", "project": "Cloudflare Workers AI speech-to-text", "segment": "Speech-to-text API", "maker": "Cloudflare"}, "obs": [["2026-10-19", 2012441]]}, "npm-cloudflare": {"entity": "cloudflare-workers-ai-whisper", "label": "cloudflare (npm)", "dims": {"package": "cloudflare", "ecosystem": "npm", "project": "Cloudflare Workers AI speech-to-text", "segment": "Speech-to-text API", "maker": "Cloudflare"}, "obs": [["2026-10-19", 13493182]]}, "pypi-pocketsphinx": {"entity": "cmu-sphinx", "label": "pocketsphinx (PyPI)", "dims": {"package": "pocketsphinx", "ecosystem": "PyPI", "project": "CMU Sphinx (PocketSphinx)", "segment": "Open model", "maker": "Carnegie Mellon University"}, "obs": [["2026-10-19", 511134]]}, "pypi-stt": {"entity": "coqui-stt", "label": "stt (PyPI)", "dims": {"package": "stt", "ecosystem": "PyPI", "project": "Coqui STT", "segment": "Open model", "maker": "Coqui"}, "obs": [["2026-10-19", 1211]]}, "pypi-deepgram-sdk": {"entity": "deepgram", "label": "deepgram-sdk (PyPI)", "dims": {"package": "deepgram-sdk", "ecosystem": "PyPI", "project": "Deepgram", "segment": "Speech-to-text API", "maker": "Deepgram"}, "obs": [["2026-10-19", 3166523]]}, "npm-deepgram-sdk": {"entity": "deepgram", "label": "@deepgram/sdk (npm)", "dims": {"package": "@deepgram/sdk", "ecosystem": "npm", "project": "Deepgram", "segment": "Speech-to-text API", "maker": "Deepgram"}, "obs": [["2026-10-19", 4092784]]}, "pypi-elevenlabs": {"entity": "elevenlabs-scribe", "label": "elevenlabs (PyPI)", "dims": {"package": "elevenlabs", "ecosystem": "PyPI", "project": "ElevenLabs Scribe", "segment": "Speech-to-text API", "maker": "ElevenLabs"}, "obs": [["2026-10-19", 9073441]]}, "npm-elevenlabs-elevenlabs-js": {"entity": "elevenlabs-scribe", "label": "@elevenlabs/elevenlabs-js (npm)", "dims": {"package": "@elevenlabs/elevenlabs-js", "ecosystem": "npm", "project": "ElevenLabs Scribe", "segment": "Speech-to-text API", "maker": "ElevenLabs"}, "obs": [["2026-10-19", 3970853]]}, "pypi-espnet": {"entity": "espnet", "label": "espnet (PyPI)", "dims": {"package": "espnet", "ecosystem": "PyPI", "project": "ESPnet", "segment": "Open model", "maker": "ESPnet developers"}, "obs": [["2026-10-19", 22999]]}, "pypi-fal-client": {"entity": "fal-speech-to-text", "label": "fal-client (PyPI)", "dims": {"package": "fal-client", "ecosystem": "PyPI", "project": "fal speech-to-text", "segment": "Speech-to-text API", "maker": "fal"}, "obs": [["2026-10-19", 2886801]]}, "npm-fal-ai-client": {"entity": "fal-speech-to-text", "label": "@fal-ai/client (npm)", "dims": {"package": "@fal-ai/client", "ecosystem": "npm", "project": "fal speech-to-text", "segment": "Speech-to-text API", "maker": "fal"}, "obs": [["2026-10-19", 6817609]]}, "pypi-faster-whisper": {"entity": "faster-whisper", "label": "faster-whisper (PyPI)", "dims": {"package": "faster-whisper", "ecosystem": "PyPI", "project": "faster-whisper", "segment": "Open model", "maker": "SYSTRAN"}, "obs": [["2026-10-19", 9614222]]}, "pypi-fireworks-ai": {"entity": "fireworks-ai-audio", "label": "fireworks-ai (PyPI)", "dims": {"package": "fireworks-ai", "ecosystem": "PyPI", "project": "Fireworks AI audio transcription", "segment": "Speech-to-text API", "maker": "Fireworks AI"}, "obs": [["2026-10-19", 1157786]]}, "pypi-funasr": {"entity": "funasr", "label": "funasr (PyPI)", "dims": {"package": "funasr", "ecosystem": "PyPI", "project": "FunASR", "segment": "Open model", "maker": "ModelScope"}, "obs": [["2026-10-19", 272534]]}, "pypi-gigaam": {"entity": "gigaam", "label": "gigaam (PyPI)", "dims": {"package": "gigaam", "ecosystem": "PyPI", "project": "GigaAM", "segment": "Open model", "maker": "SaluteDevices (Sber)"}, "obs": [["2026-10-19", 1692]]}, "npm-gladiaio-sdk": {"entity": "gladia", "label": "@gladiaio/sdk (npm)", "dims": {"package": "@gladiaio/sdk", "ecosystem": "npm", "project": "Gladia", "segment": "Speech-to-text API", "maker": "Gladia"}, "obs": [["2026-10-19", 18223]]}, "pypi-google-cloud-speech": {"entity": "google-cloud-speech-to-text", "label": "google-cloud-speech (PyPI)", "dims": {"package": "google-cloud-speech", "ecosystem": "PyPI", "project": "Google Cloud Speech-to-Text", "segment": "Speech-to-text API", "maker": "Google Cloud"}, "obs": [["2026-10-19", 15131032]]}, "npm-google-cloud-speech": {"entity": "google-cloud-speech-to-text", "label": "@google-cloud/speech (npm)", "dims": {"package": "@google-cloud/speech", "ecosystem": "npm", "project": "Google Cloud Speech-to-Text", "segment": "Speech-to-text API", "maker": "Google Cloud"}, "obs": [["2026-10-19", 2831975]]}, "pypi-google-genai": {"entity": "google-gemini-transcribe", "label": "google-genai (PyPI)", "dims": {"package": "google-genai", "ecosystem": "PyPI", "project": "Gemini API transcription", "segment": "Speech-to-text API", "maker": "Google"}, "obs": [["2026-10-19", 137607856]]}, "npm-google-genai": {"entity": "google-gemini-transcribe", "label": "@google/genai (npm)", "dims": {"package": "@google/genai", "ecosystem": "npm", "project": "Gemini API transcription", "segment": "Speech-to-text API", "maker": "Google"}, "obs": [["2026-10-19", 102468836]]}, "pypi-groq": {"entity": "groq-speech-to-text", "label": "groq (PyPI)", "dims": {"package": "groq", "ecosystem": "PyPI", "project": "GroqCloud Speech to Text", "segment": "Speech-to-text API", "maker": "Groq"}, "obs": [["2026-10-19", 16795477]]}, "npm-groq-sdk": {"entity": "groq-speech-to-text", "label": "groq-sdk (npm)", "dims": {"package": "groq-sdk", "ecosystem": "npm", "project": "GroqCloud Speech to Text", "segment": "Speech-to-text API", "maker": "Groq"}, "obs": [["2026-10-19", 3810140]]}, "pypi-ibm-watson": {"entity": "ibm-watson-speech-to-text", "label": "ibm-watson (PyPI)", "dims": {"package": "ibm-watson", "ecosystem": "PyPI", "project": "IBM Watson Speech to Text", "segment": "Speech-to-text API", "maker": "IBM"}, "obs": [["2026-10-19", 50699]]}, "npm-ibm-watson": {"entity": "ibm-watson-speech-to-text", "label": "ibm-watson (npm)", "dims": {"package": "ibm-watson", "ecosystem": "npm", "project": "IBM Watson Speech to Text", "segment": "Speech-to-text API", "maker": "IBM"}, "obs": [["2026-10-19", 44739]]}, "pypi-insanely-fast-whisper": {"entity": "insanely-fast-whisper", "label": "insanely-fast-whisper (PyPI)", "dims": {"package": "insanely-fast-whisper", "ecosystem": "PyPI", "project": "insanely-fast-whisper", "segment": "Open model", "maker": "Vaibhav Srivastav"}, "obs": [["2026-10-19", 807]]}, "pypi-k2": {"entity": "k2-icefall", "label": "k2 (PyPI)", "dims": {"package": "k2", "ecosystem": "PyPI", "project": "k2 and icefall", "segment": "Open model", "maker": "Next-gen Kaldi team"}, "obs": [["2026-10-19", 1947]]}, "pypi-lightning-whisper-mlx": {"entity": "lightning-whisper-mlx", "label": "lightning-whisper-mlx (PyPI)", "dims": {"package": "lightning-whisper-mlx", "ecosystem": "PyPI", "project": "Lightning Whisper MLX", "segment": "Open model", "maker": "Mustafa Aljadery"}, "obs": [["2026-10-19", 378]]}, "pypi-mistralai": {"entity": "mistral-voxtral-transcribe", "label": "mistralai (PyPI)", "dims": {"package": "mistralai", "ecosystem": "PyPI", "project": "Mistral Voxtral Transcribe", "segment": "Speech-to-text API", "maker": "Mistral AI"}, "obs": [["2026-10-19", 16185864]]}, "npm-mistralai-mistralai": {"entity": "mistral-voxtral-transcribe", "label": "@mistralai/mistralai (npm)", "dims": {"package": "@mistralai/mistralai", "ecosystem": "npm", "project": "Mistral Voxtral Transcribe", "segment": "Speech-to-text API", "maker": "Mistral AI"}, "obs": [["2026-10-19", 32317341]]}, "pypi-mlx-whisper": {"entity": "mlx-whisper", "label": "mlx-whisper (PyPI)", "dims": {"package": "mlx-whisper", "ecosystem": "PyPI", "project": "MLX Whisper", "segment": "Open model", "maker": "Apple MLX team"}, "obs": [["2026-10-19", 340121]]}, "pypi-moonshine-voice": {"entity": "moonshine", "label": "moonshine-voice (PyPI)", "dims": {"package": "moonshine-voice", "ecosystem": "PyPI", "project": "Moonshine", "segment": "Open model", "maker": "Moonshine AI"}, "obs": [["2026-10-19", 37860]]}, "pypi-useful-moonshine-onnx": {"entity": "moonshine", "label": "useful-moonshine-onnx (PyPI)", "dims": {"package": "useful-moonshine-onnx", "ecosystem": "PyPI", "project": "Moonshine", "segment": "Open model", "maker": "Moonshine AI"}, "obs": [["2026-10-19", 39401]]}, "npm-moonshine-ai-moonshine-js": {"entity": "moonshine", "label": "@moonshine-ai/moonshine-js (npm)", "dims": {"package": "@moonshine-ai/moonshine-js", "ecosystem": "npm", "project": "Moonshine", "segment": "Open model", "maker": "Moonshine AI"}, "obs": [["2026-10-19", 15549]]}, "pypi-deepspeech": {"entity": "mozilla-deepspeech", "label": "deepspeech (PyPI)", "dims": {"package": "deepspeech", "ecosystem": "PyPI", "project": "Mozilla DeepSpeech", "segment": "Open model", "maker": "Mozilla"}, "obs": [["2026-10-19", 2375]]}, "npm-deepspeech": {"entity": "mozilla-deepspeech", "label": "deepspeech (npm)", "dims": {"package": "deepspeech", "ecosystem": "npm", "project": "Mozilla DeepSpeech", "segment": "Open model", "maker": "Mozilla"}, "obs": [["2026-10-19", 784]]}, "pypi-nemo-toolkit": {"entity": "nemo-toolkit", "label": "nemo-toolkit (PyPI)", "dims": {"package": "nemo-toolkit", "ecosystem": "PyPI", "project": "NVIDIA NeMo", "segment": "Open model", "maker": "NVIDIA"}, "obs": [["2026-10-19", 445752]]}, "pypi-nvidia-riva-client": {"entity": "nvidia-riva", "label": "nvidia-riva-client (PyPI)", "dims": {"package": "nvidia-riva-client", "ecosystem": "PyPI", "project": "NVIDIA Riva", "segment": "Open model", "maker": "NVIDIA"}, "obs": [["2026-10-19", 274349]]}, "pypi-omnilingual-asr": {"entity": "omnilingual-asr", "label": "omnilingual-asr (PyPI)", "dims": {"package": "omnilingual-asr", "ecosystem": "PyPI", "project": "Omnilingual ASR", "segment": "Open model", "maker": "Meta AI"}, "obs": [["2026-10-19", 5257]]}, "pypi-onnx-asr": {"entity": "onnx-asr", "label": "onnx-asr (PyPI)", "dims": {"package": "onnx-asr", "ecosystem": "PyPI", "project": "onnx-asr", "segment": "Open model", "maker": "istupakov"}, "obs": [["2026-10-19", 157573]]}, "pypi-openai": {"entity": "openai-speech-to-text", "label": "openai (PyPI)", "dims": {"package": "openai", "ecosystem": "PyPI", "project": "OpenAI Speech to Text API", "segment": "Speech-to-text API", "maker": "OpenAI"}, "obs": [["2026-10-19", 295856631]]}, "npm-openai": {"entity": "openai-speech-to-text", "label": "openai (npm)", "dims": {"package": "openai", "ecosystem": "npm", "project": "OpenAI Speech to Text API", "segment": "Speech-to-text API", "maker": "OpenAI"}, "obs": [["2026-10-19", 175958798]]}, "pypi-oci": {"entity": "oracle-oci-speech", "label": "oci (PyPI)", "dims": {"package": "oci", "ecosystem": "PyPI", "project": "Oracle Cloud Infrastructure Speech", "segment": "Speech-to-text API", "maker": "Oracle"}, "obs": [["2026-10-19", 5164205]]}, "npm-oci-aispeech": {"entity": "oracle-oci-speech", "label": "oci-aispeech (npm)", "dims": {"package": "oci-aispeech", "ecosystem": "npm", "project": "Oracle Cloud Infrastructure Speech", "segment": "Speech-to-text API", "maker": "Oracle"}, "obs": [["2026-10-19", 473238]]}, "pypi-paddlespeech": {"entity": "paddlespeech", "label": "paddlespeech (PyPI)", "dims": {"package": "paddlespeech", "ecosystem": "PyPI", "project": "PaddleSpeech", "segment": "Open model", "maker": "PaddlePaddle"}, "obs": [["2026-10-19", 1112]]}, "pypi-parakeet-mlx": {"entity": "parakeet-mlx", "label": "parakeet-mlx (PyPI)", "dims": {"package": "parakeet-mlx", "ecosystem": "PyPI", "project": "Parakeet MLX", "segment": "Open model", "maker": "Senstella"}, "obs": [["2026-10-19", 37644]]}, "pypi-pvcheetah": {"entity": "picovoice-cheetah", "label": "pvcheetah (PyPI)", "dims": {"package": "pvcheetah", "ecosystem": "PyPI", "project": "Picovoice Cheetah", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 2012]]}, "npm-picovoice-cheetah-node": {"entity": "picovoice-cheetah", "label": "@picovoice/cheetah-node (npm)", "dims": {"package": "@picovoice/cheetah-node", "ecosystem": "npm", "project": "Picovoice Cheetah", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 518]]}, "npm-picovoice-cheetah-web": {"entity": "picovoice-cheetah", "label": "@picovoice/cheetah-web (npm)", "dims": {"package": "@picovoice/cheetah-web", "ecosystem": "npm", "project": "Picovoice Cheetah", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 909]]}, "pypi-pvleopard": {"entity": "picovoice-leopard", "label": "pvleopard (PyPI)", "dims": {"package": "pvleopard", "ecosystem": "PyPI", "project": "Picovoice Leopard", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 1752]]}, "npm-picovoice-leopard-node": {"entity": "picovoice-leopard", "label": "@picovoice/leopard-node (npm)", "dims": {"package": "@picovoice/leopard-node", "ecosystem": "npm", "project": "Picovoice Leopard", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 843]]}, "npm-picovoice-leopard-web": {"entity": "picovoice-leopard", "label": "@picovoice/leopard-web (npm)", "dims": {"package": "@picovoice/leopard-web", "ecosystem": "npm", "project": "Picovoice Leopard", "segment": "Speech-to-text API", "maker": "Picovoice"}, "obs": [["2026-10-19", 524]]}, "pypi-qwen-asr": {"entity": "qwen3-asr", "label": "qwen-asr (PyPI)", "dims": {"package": "qwen-asr", "ecosystem": "PyPI", "project": "Qwen3-ASR", "segment": "Open model", "maker": "Alibaba Cloud (Qwen team)"}, "obs": [["2026-10-19", 114347]]}, "pypi-replicate": {"entity": "replicate-whisper", "label": "replicate (PyPI)", "dims": {"package": "replicate", "ecosystem": "PyPI", "project": "Replicate speech-to-text models", "segment": "Speech-to-text API", "maker": "Replicate"}, "obs": [["2026-10-19", 1526037]]}, "npm-replicate": {"entity": "replicate-whisper", "label": "replicate (npm)", "dims": {"package": "replicate", "ecosystem": "npm", "project": "Replicate speech-to-text models", "segment": "Speech-to-text API", "maker": "Replicate"}, "obs": [["2026-10-19", 2470241]]}, "pypi-rev-ai": {"entity": "rev-ai", "label": "rev-ai (PyPI)", "dims": {"package": "rev-ai", "ecosystem": "PyPI", "project": "Rev AI", "segment": "Speech-to-text API", "maker": "Rev"}, "obs": [["2026-10-19", 563673]]}, "npm-revai-node-sdk": {"entity": "rev-ai", "label": "revai-node-sdk (npm)", "dims": {"package": "revai-node-sdk", "ecosystem": "npm", "project": "Rev AI", "segment": "Speech-to-text API", "maker": "Rev"}, "obs": [["2026-10-19", 55905]]}, "pypi-sarvamai": {"entity": "sarvam-speech-to-text", "label": "sarvamai (PyPI)", "dims": {"package": "sarvamai", "ecosystem": "PyPI", "project": "Sarvam Speech to Text", "segment": "Speech-to-text API", "maker": "Sarvam"}, "obs": [["2026-10-19", 140661]]}, "npm-sarvamai": {"entity": "sarvam-speech-to-text", "label": "sarvamai (npm)", "dims": {"package": "sarvamai", "ecosystem": "npm", "project": "Sarvam Speech to Text", "segment": "Speech-to-text API", "maker": "Sarvam"}, "obs": [["2026-10-19", 45373]]}, "pypi-sherpa-onnx": {"entity": "sherpa-onnx", "label": "sherpa-onnx (PyPI)", "dims": {"package": "sherpa-onnx", "ecosystem": "PyPI", "project": "sherpa-onnx", "segment": "Open model", "maker": "Next-gen Kaldi team"}, "obs": [["2026-10-19", 1614806]]}, "npm-sherpa-onnx": {"entity": "sherpa-onnx", "label": "sherpa-onnx (npm)", "dims": {"package": "sherpa-onnx", "ecosystem": "npm", "project": "sherpa-onnx", "segment": "Open model", "maker": "Next-gen Kaldi team"}, "obs": [["2026-10-19", 455585]]}, "npm-sherpa-onnx-node": {"entity": "sherpa-onnx", "label": "sherpa-onnx-node (npm)", "dims": {"package": "sherpa-onnx-node", "ecosystem": "npm", "project": "sherpa-onnx", "segment": "Open model", "maker": "Next-gen Kaldi team"}, "obs": [["2026-10-19", 2109793]]}, "pypi-soniox": {"entity": "soniox", "label": "soniox (PyPI)", "dims": {"package": "soniox", "ecosystem": "PyPI", "project": "Soniox", "segment": "Speech-to-text API", "maker": "Soniox"}, "obs": [["2026-10-19", 588965]]}, "npm-soniox-node": {"entity": "soniox", "label": "@soniox/node (npm)", "dims": {"package": "@soniox/node", "ecosystem": "npm", "project": "Soniox", "segment": "Speech-to-text API", "maker": "Soniox"}, "obs": [["2026-10-19", 87728]]}, "npm-soniox-client": {"entity": "soniox", "label": "@soniox/client (npm)", "dims": {"package": "@soniox/client", "ecosystem": "npm", "project": "Soniox", "segment": "Speech-to-text API", "maker": "Soniox"}, "obs": [["2026-10-19", 102409]]}, "npm-soniox-speech-to-text-web": {"entity": "soniox", "label": "@soniox/speech-to-text-web (npm)", "dims": {"package": "@soniox/speech-to-text-web", "ecosystem": "npm", "project": "Soniox", "segment": "Speech-to-text API", "maker": "Soniox"}, "obs": [["2026-10-19", 141454]]}, "pypi-speechbrain": {"entity": "speechbrain", "label": "speechbrain (PyPI)", "dims": {"package": "speechbrain", "ecosystem": "PyPI", "project": "SpeechBrain", "segment": "Open model", "maker": "SpeechBrain"}, "obs": [["2026-10-19", 1015647]]}, "pypi-speechmatics-batch": {"entity": "speechmatics", "label": "speechmatics-batch (PyPI)", "dims": {"package": "speechmatics-batch", "ecosystem": "PyPI", "project": "Speechmatics", "segment": "Speech-to-text API", "maker": "Speechmatics"}, "obs": [["2026-10-19", 61951]]}, "pypi-speechmatics-rt": {"entity": "speechmatics", "label": "speechmatics-rt (PyPI)", "dims": {"package": "speechmatics-rt", "ecosystem": "PyPI", "project": "Speechmatics", "segment": "Speech-to-text API", "maker": "Speechmatics"}, "obs": [["2026-10-19", 237868]]}, "pypi-speechmatics-sdk": {"entity": "speechmatics", "label": "speechmatics-sdk (PyPI)", "dims": {"package": "speechmatics-sdk", "ecosystem": "PyPI", "project": "Speechmatics", "segment": "Speech-to-text API", "maker": "Speechmatics"}, "obs": [["2026-10-19", 13]]}, "npm-speechmatics-real-time-client": {"entity": "speechmatics", "label": "@speechmatics/real-time-client (npm)", "dims": {"package": "@speechmatics/real-time-client", "ecosystem": "npm", "project": "Speechmatics", "segment": "Speech-to-text API", "maker": "Speechmatics"}, "obs": [["2026-10-19", 192130]]}, "npm-speechmatics-batch-client": {"entity": "speechmatics", "label": "@speechmatics/batch-client (npm)", "dims": {"package": "@speechmatics/batch-client", "ecosystem": "npm", "project": "Speechmatics", "segment": "Speech-to-text API", "maker": "Speechmatics"}, "obs": [["2026-10-19", 119664]]}, "pypi-speechrecognition": {"entity": "speechrecognition-python", "label": "SpeechRecognition (PyPI)", "dims": {"package": "SpeechRecognition", "ecosystem": "PyPI", "project": "SpeechRecognition (Python)", "segment": "Open model", "maker": "Anthony Zhang (Uberi)"}, "obs": [["2026-10-19", 9042851]]}, "pypi-telnyx": {"entity": "telnyx-speech-to-text", "label": "telnyx (PyPI)", "dims": {"package": "telnyx", "ecosystem": "PyPI", "project": "Telnyx Speech-to-Text API", "segment": "Speech-to-text API", "maker": "Telnyx"}, "obs": [["2026-10-19", 682274]]}, "npm-telnyx": {"entity": "telnyx-speech-to-text", "label": "telnyx (npm)", "dims": {"package": "telnyx", "ecosystem": "npm", "project": "Telnyx Speech-to-Text API", "segment": "Speech-to-text API", "maker": "Telnyx"}, "obs": [["2026-10-19", 1582453]]}, "pypi-tencentcloud-sdk-python-asr": {"entity": "tencent-cloud-asr", "label": "tencentcloud-sdk-python-asr (PyPI)", "dims": {"package": "tencentcloud-sdk-python-asr", "ecosystem": "PyPI", "project": "Tencent Cloud ASR", "segment": "Speech-to-text API", "maker": "Tencent Cloud"}, "obs": [["2026-10-19", 8787]]}, "npm-tencentcloud-sdk-nodejs-asr": {"entity": "tencent-cloud-asr", "label": "tencentcloud-sdk-nodejs-asr (npm)", "dims": {"package": "tencentcloud-sdk-nodejs-asr", "ecosystem": "npm", "project": "Tencent Cloud ASR", "segment": "Speech-to-text API", "maker": "Tencent Cloud"}, "obs": [["2026-10-19", 7910]]}, "pypi-together": {"entity": "together-ai-audio", "label": "together (PyPI)", "dims": {"package": "together", "ecosystem": "PyPI", "project": "Together AI audio transcription", "segment": "Speech-to-text API", "maker": "Together AI"}, "obs": [["2026-10-19", 1503145]]}, "npm-together-ai": {"entity": "together-ai-audio", "label": "together-ai (npm)", "dims": {"package": "together-ai", "ecosystem": "npm", "project": "Together AI audio transcription", "segment": "Speech-to-text API", "maker": "Together AI"}, "obs": [["2026-10-19", 413434]]}, "pypi-vosk": {"entity": "vosk", "label": "vosk (PyPI)", "dims": {"package": "vosk", "ecosystem": "PyPI", "project": "Vosk", "segment": "Open model", "maker": "Alpha Cephei"}, "obs": [["2026-10-19", 633645]]}, "npm-vosk": {"entity": "vosk", "label": "vosk (npm)", "dims": {"package": "vosk", "ecosystem": "npm", "project": "Vosk", "segment": "Open model", "maker": "Alpha Cephei"}, "obs": [["2026-10-19", 8270]]}, "pypi-openai-whisper": {"entity": "whisper", "label": "openai-whisper (PyPI)", "dims": {"package": "openai-whisper", "ecosystem": "PyPI", "project": "Whisper", "segment": "Open model", "maker": "OpenAI"}, "obs": [["2026-10-19", 4986176]]}, "pypi-whisper-live": {"entity": "whisperlive", "label": "whisper-live (PyPI)", "dims": {"package": "whisper-live", "ecosystem": "PyPI", "project": "WhisperLive", "segment": "Open model", "maker": "Collabora"}, "obs": [["2026-10-19", 1660]]}, "pypi-whisperlivekit": {"entity": "whisperlivekit", "label": "whisperlivekit (PyPI)", "dims": {"package": "whisperlivekit", "ecosystem": "PyPI", "project": "WhisperLiveKit", "segment": "Open model", "maker": "Quentin Fuxa"}, "obs": [["2026-10-19", 6366]]}, "pypi-whisperx": {"entity": "whisperx", "label": "whisperx (PyPI)", "dims": {"package": "whisperx", "ecosystem": "PyPI", "project": "WhisperX", "segment": "Open model", "maker": "Max Bain"}, "obs": [["2026-10-19", 342919]]}, "pypi-xai-sdk": {"entity": "xai-grok-speech-to-text", "label": "xai-sdk (PyPI)", "dims": {"package": "xai-sdk", "ecosystem": "PyPI", "project": "Grok Speech to Text", "segment": "Speech-to-text API", "maker": "SpaceXSI (xAI)"}, "obs": [["2026-10-19", 4773444]]}}}}