Voice & audio

Speech-to-text & transcription

381 agents · most starred first

Speech-to-text & transcription, page 4 of 4

agenticasr★ 1

gradio mcp-server region:us

whisper-ai

Whisper AI review, features, use cases and alternatives (5/5 from 6 reviews): A Chrome extension for speech-to-text transcription and AI voice typing.

AssemblyAI

Transcribe and understand speech accurately with advanced AI models.

@remotion/openai-whisper

Work with the output of the OpenAI Whisper API

@ai-sdk/deepgram

The **[Deepgram provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepgram)** for the [AI SDK](https://ai-sdk.dev/docs) contains transcription model support for the Deepgram transcription API and speech model support for the Deepgram text-to-speech

@ai-sdk/assemblyai

The **[AssemblyAI provider](https://ai-sdk.dev/providers/ai-sdk-providers/assemblyai)** for the [AI SDK](https://ai-sdk.dev/docs) contains transcription model support for the AssemblyAI transcription API.

@ai-sdk/gladia

The **[Gladia provider](https://ai-sdk.dev/providers/ai-sdk-providers/assemblyai)** for the [AI SDK](https://ai-sdk.dev/docs) contains transcription model support for the Gladia transcription API.

@ai-sdk/revai

The **[Rev.ai provider](https://ai-sdk.dev/providers/ai-sdk-providers/revai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the Rev.ai transcription API.

revai-node-sdk

Rev AI makes speech applications easy to build!

@deepgram/sdk

![Built with Fern](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen) [![npm version](https://img.shields.io/npm/v/@deepgram/sdk)](https://www.npmjs.com/package/@deepgram/sdk) [![Node.js 18+](https://img.shields.io/badge/node-18+-b

@soniox/vercel-ai-sdk-provider

Soniox transcription provider for the Vercel AI SDK.

GovGPT-denoise

A simple and short denoising algorithm to denoise maximum amount of noise from an audio

ai-agent-video-transcription

Multi-agent AI system for video transcription using OpenAI Whisper, ChromaDB, and AutoGen

asb-groq-sub

A tool for downloading YouTube audio, generating subtitles, and sending them to an HTTP endpoint.

assemblyai-haystack

AssemblyAI Haystack Integration

audio-xai-fragility

A project about Audio models and it's fragility

cjm-transcription-plugin-gemini

Google Gemini API plugin for the cjm-transcription-plugin-system library - provides speech-to-text transcription with configurable model selection and parameter control.

cjm-transcription-plugin-voxtral-vllm

Mistral Voxtral plugin for the cjm-transcription-plugin-system library - provides local speech-to-text transcription through vLLM with configurable model selection and parameter control.

cohere-transcribe-cli

Local CLI for Cohere Transcribe (open-source 2B Conformer ASR).

dict-from-dragonmapper

Command-line interface (CLI) to create a pronunciation dictionary by looking up IPA transcriptions using dragonmapper including the possibility of ignoring punctuation and splitting words on hyphens before transcribing them.

distillmos

Efficient speech quality assessment learned from SSL-based speech quality assessment model

dragonfly

Speech recognition extension library

dragonfly2

Speech recognition extension library

farm-haystack-speech2text

Haystack node to convert audio files into Documents.

finetune-openai-whisper

A complete pipeline for fine-tuning OpenAI's Whisper ASR model using PyTorch Lightning

fungpt

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

funllm

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

gemini-audio-transcription

Audio transcription and alignment library using Google Gemini API for TTS labeling

groq-whisper-transcribe

A simple script that uses the Groq API to transcribe audio files using the Whisper model

improve-diarization-with-llm

This tool can take a long script (greater than 10 hours) of diarized content and improve the diarization by prompting an LLM model to look for obviously incorrect attribution and fix it.

langchain-soniox

LangChain integration for Soniox

llama-index-readers-assemblyai

llama-index readers assemblyai integration

llm-groq-whisper

Transcribe audio using the Groq.com Whisper API

llm-whisper-api

Run transcriptions using the OpenAI Whisper API

openai-whisper

Robust Speech Recognition via Large-Scale Weak Supervision

openai-whisper-api-cli

Simple CLI wrapper for OpenAI Speech-to-Text API

openai_stt

Speech-to-Text tool using Whisper, PyAudio, and VAD.

pyconverters-openai_audio

OpenAIAudio converter

sonusai-asr-openai-whisper

OpenAI Whisper ASR tools for SonusAI

stream-translator-gpt

Command line tool to transcribe & translate audio from livestreams in real time

swarmauri_llm_whisper

Swarmauri Whisper LLM adapters from swarmauri_standard.

vision-agents-plugins-assemblyai

AssemblyAI streaming STT integration for Vision Agents

vision-agents-plugins-deepgram

Deepgram STT and TTS integration for Vision Agents

vision-agents-plugins-fast-whisper

Fast Whisper STT integration for Vision Agents

vision-agents-plugins-mistral

Mistral Voxtral STT integration for Vision Agents

vision-agents-plugins-moonshine

Moonshine STT integration for Vision Agents

vision-agents-plugins-wizper

Wizper plugin for Vision Agents

whisper-openai

Robust Speech Recognition via Large-Scale Weak Supervision

Speechmatics

Speech AI: Accurate speech-to-text and natural text-to-speech.

groq-whisper-cli

Groq Whisper 多 Key 并发语音转写 CLI 工具

@redaksjon/protokoll-engine

Processing engine for Protokoll - transcription pipeline, agentic execution, routing, and LLM integration

assemblyai

The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription and text-to-speech.

claude-purr

Local dictation backend for Claude Code (macOS, Apple Silicon) — on-device Whisper, "Hey Claude" wake word, @-file tagging, voice daemon.

funasr-haystack

FunASR speech-to-text transcriber for Haystack

langchain-funasr

LangChain integration for FunASR (SenseVoice / Paraformer / Fun-ASR-Nano) speech-to-text

llama-index-readers-funasr

llama-index readers FunASR (SenseVoice / Paraformer / Fun-ASR-Nano) integration

crispasr-agent-transcriber

Local CrispASR transcription workflow for Codex and MCP agents.

whisper-haystack

Haystack integration for whisper

memoveraa

Memoveraa review: compare features, pricing, use cases, access model, and alternatives for this Memory agent in 2026. AI tool that transcribes meetings and generates searchable summaries.

memovera

Memovera review: compare features, pricing, use cases, access model, and alternatives for this Memory agent in 2026. AI tool that transcribes meetings and generates searchable summaries.

cohere-transcribe

Unofficial high-throughput batch inference for Cohere Arabic/English ASR

cohere-transcribe-arabic

Unofficial high-throughput batch inference for Cohere Arabic/English ASR

coherex

Time-Accurate Automatic Speech Recognition using Cohere Transcribe, with word-level timestamps and speaker diarization.

runapi-openai-transcription

RunAPI OpenAI Transcription SDK for speech-to-text integration

video-to-llm

Turn hours of local video into timestamped, citable, LLM-ready text. Fully offline. Resumable.

pi-telegram-stt

STT orchestrator + bundled OpenAI-compatible STT provider for the Pi coding agent + @llblab/pi-telegram bridge. Wraps the inbound voice/audio pipeline (downloads voice notes, runs STT via the in-package OpenAI client, sends a 🎙️ echo to the user, and fee

gemini-transcribe-wrapper

CLI and Python API to transcribe videos longer than 30 minutes with gemini-3.5-transcribe while mitigating free-tier 429 errors

Scribecast

Scribecast — turn a video into text. Give it a YouTube URL and get the spoken content back as plain text, timed segments, SRT or WebVTT, with the title, channel and duration. It reads the caption track the video already publishes (human-written when there is one, YouTube speech recognition otherwise), so a video with captions disabled returns an honest 404 rather than an invented transcript. Genuinely free: no model runs behind it. Optional free server-side translation.

keebye

Keebye review: compare features, pricing, use cases, access model, and alternatives for this Productivity agent in 2026. On-device macOS voice dictation for developers working across multiple tools

@ai-coustics/aic-sdk-linux-x64-gnu

Node.js package of ai-coustics SDK

speechmatics-agent-stt

Speechmatics Agent STT Python client for agent transcription

convert-audio-to-text

Convert Audio to Text review: compare features, pricing, use cases, access model, and alternatives for this Productivity agent in 2026. Rated 5/5 from 5 verified reviews. Turn audio, video, and YouTube links into accurate transcripts with timestamps and AI summaries.

notepipe-asr-llama

llama.cpp speech recognition adapter for notepipe

ragleap-voice

Pre-alpha, open, local speech-to-text and text-to-speech: licence-checked manifest, hash-verified downloads, transcribe() and synthesize() with a Whisper engine (optional extra) and an Indic Parler-TTS engine (own environment). Every model is unverified.

rocketscribe

RocketScribe review: compare features, pricing, use cases, access model, and alternatives for this Voice AI Agents agent in 2026. Accurate, timestamped transcripts of audio and video in 90+ languages. Free to try, no sign-up.

pi-voice-stt

Provider-agnostic speech-to-text for Pi, with interactive voice dictation and audio file transcription.

llama-index-readers-lokutor

llama-index readers lokutor integration: transcribe audio into Documents with Lokutor speech-to-text

LinkToText

Free Instagram transcript generator. Paste a public Reel or video URL and get a clean, searchable transcript for captions, subtitles, and summaries — no download or extension.

AccurateScribe.ai

AccurateScribe.ai is an AI transcription tool that turns meeting recordings, interviews, podcasts, and video files into accurate written transcripts with speaker detection. Freemium pricing.

Transcribe Video: To The Text

iPhone app that turns video and audio files, YouTube/Vimeo links and live voice recordings into editable text transcripts. Includes speaker-split view, AI summaries and TXT/DOCX export, with 51 recognition languages. Free tier to try it; Pro subscription for longer recordings. iOS: https://apps.apple.com/us/app/transcribe-video-to-the-text/id6757491608

ScribeAny

More in Voice & audio