Unfragile

The request names ExecuTorch and Whisper for on-device speech-to-text in React Native. None of the candidate sources documents an ExecuTorch-based Whisper Tiny React Native package, so the closest matches are general speech-to-text services that expose Whisper-family or transcription actions. Replicate hosts a Whisper tiny model callable through an API 111, and LocalAI offers a transcription action on self-hosted hardware 717.

1
Replicatereplicate.comverified and signed
Hosted model API that runs open-source models, including a Whisper action that converts speech to text with tiny, small, base and large-v3 models 111.
Website Docs Pricing Get started
for agents: zsxkib/whisper-lazyloading
2
LocalAIlocalai.ioverified and signed
Open source AI engine that runs models locally, with a Transcribe Audio action that turns speech in an audio file into text 717.
Website Docs
+6 community tools built for it
for agents: transcribe_audio · text_to_speech · ask_localai
3
ElevenLabselevenlabs.iofound in code, not yet checked
Voice platform with a speech-to-text action that transcribes audio using ElevenLabs Scribe v2 616.
Website Docs Pricing Get started
official:MCP server · ElevenLabs+58 community tools built for it
for agents: speech_to_text · speech-to-text · speech_to_speech

Sources

1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
6Free AI Voice Generator & Voice Agents Platform | ElevenLabselevenlabs.io · read 2026-10-29
7LocalAI · Make AI run on every machinelocalai.io · read 2026-10-29
11zsxkib/whisper-lazyloading: declares "zsxkib/whisper-lazyloading" (the record we read and signed)unfragile.ai · read 2026-10-24
16ElevenLabs MCP Server: declares "speech_to_text" (the record we read)github.com · read 2026-10-24
17LocalAI (Activepieces): declares "transcribe_audio" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

zsxkib/whisper-lazyloading · zsxkib/whisper-lazyloading verified and signed
Convert speech in audio to text w/ `tiny`, `small`, `base`, and `large-v3` models
openai/whisper · openai/whisper verified and signed
Convert speech in audio to text
soykertje/whisper · soykertje/whisper verified and signed
Convert speech in audio to text
turian/insanely-fast-whisper-with-video · turian/insanely-fast-whisper-with-video verified and signed
whisper-large-v3, incredibly fast, with video transcription
vaibhavs10/incredibly-fast-whisper · vaibhavs10/incredibly-fast-whisper verified and signed
whisper-large-v3, incredibly fast, powered by Hugging Face Transformers! 🤗
thomasmol/whisper-diarization · thomasmol/whisper-diarization verified and signed
⚡️ Blazing fast audio transcription with speaker diarization | Whisper Large V3 Turbo & pyannote 4.0 community-1 | word & sentence level timestamps | prompt
rafaelgalle/whisper-diarization-advanced · rafaelgalle/whisper-diarization-advanced verified and signed
Ultra-fast, customizable speech-to-text and speaker diarization for noisy, multi-speaker audio. Includes advanced noise reduction, stereo channel support, and flexible audio preprocessing—ideal for call centers, meetings, and podcasts.
nateraw/whisper-large-v3 · nateraw/whisper-large-v3 verified and signed
Whisper is a general-purpose speech recognition model.
cjwbw/whisper · cjwbw/whisper verified and signed
with large-v2 checkpoint
hnesk/whisper-wordtimestamps · hnesk/whisper-wordtimestamps verified and signed
openai/whisper with exposed settings for word_timestamps

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.