Search
Searching the tools indexFilters
Type
Ready to use
Build with
Connect / Integrate
Extend
Operate
Reference
Topics
More topics
Source
Ranked under Top · All Time
- 1954AI Tools
Local text-to-speech and speech-to-text over stdio using Kokoro, Parakeet and Silero VAD
github.com/cjus/audio-chat-boxOpen Source
AI Tools
- 2505AI Tools
Text-to-speech and voice cloning with inline emotion tags and 30+ language support.
Servicefish.audioFreemium
AI Tools
- 3449AI Tools
Offline speech-to-text and text-to-speech on ESP32-S3 and P4 using 4-bit quantized models
github.com/tlack/babytalk
AI Tools
- 96@microsoftAI Tools
Open-source voice AI framework with 60-minute ASR transcription, 90-minute multi-speaker TTS, and streaming synthesis.
Modelgithub.com/microsoft/vibevoiceOpen Source
@microsoft · AI Tools
- 2019AI Agents
Local Apple Silicon voice agent loop with VAD, turn detection, Parakeet speech-to-text and Phonon TTS
github.com/johnrobinsn/macvoiceOpen Source
AI Agents
- 1865AI Agents
Self-hosted runtime that streams STT, an LLM, and TTS together for low-latency voice agents.
Runtimegithub.com/samarthurs18/fusion-runtimeOpen Source
AI Agents
- 167@jamiepineAI Tools
Desktop app that clones a voice from 3 seconds of audio and generates speech locally across 23 languages.
Applicationvoicebox.shOpen Source
@jamiepine · AI Tools
- 3591Developer Tools
Self-hosted speech-to-text platform running multiple ASR models locally, in Kubernetes, or on-prem.
Servicegithub.com/nanosamurai/nanosamuraiOpen Source
Developer Tools
- 3845AI Tools
English text-to-speech model with emotion tags and voice cloning that runs on CPU
Modelhuggingface.coOpen Source
AI Tools
- 4150AI Tools
Local voice dictation that types into any app, with an AI editor that applies spoken corrections
Applicationgetlipwise.comOpen Source
AI Tools
- 3310AI Agents
Adds phone voice to existing chatbots, handling speech-to-text and text-to-speech while the bot processes text.
Serviceclawdtalk.comFreemium
AI Agents
- 4057AI Tools
Mac app that transcribes speech on-device using Google's EmbeddingGemma 2 audio embeddings.
Applicationeg2.haku.shFree
AI Tools
- 1103AI Tools
Open-source voice dictation, spoken AI assistant and meeting notes app with local speech models.
Applicationwww.speakoflow.comOpen Source
AI Tools
- 2633AI Tools
Local, offline voice dictation app that turns spoken notes into developer docs and commit messages.
Applicationdicty.ioFreemium
AI Tools
- 3716AI Tools
Terminal app that records speech, transcribes it locally or via OpenAI, and copies the text.
Applicationgithub.com/blairjordan/pastefaceOpen Source
AI Tools
- 557AI Tools
Real-time speech-to-text for Mac, Windows, and iPhone that handles technical terms like code syntax across apps.
Applicationwithaqua.comFreemium
AI Tools
- 3939AI Tools
Offline Mac and Windows app for dictation, speech-to-text and translation across seven spoken languages.
Applicationmahmoud.shFree
AI Tools
- 2321@DeepgramAIAI Tools
Text-to-speech that carries context across a whole conversation instead of reading one line at a time.
Modeldeepgram.comFreemium
@DeepgramAI · AI Tools
- 3843AI Tools
On-device macOS dictation app that transcribes speech locally with no audio ever uploaded.
Applicationjexxa.orgPaid
AI Tools
- 2610AI Tools
GGUF model for post-processing speech-to-text output with normalization, punctuation and truecasing
Modelhuggingface.co
AI Tools
- 4043AI Tools
Accented English text-to-speech model with an 8 kHz telephony mode, steered by plain-language voice descriptions
Modelhuggingface.coOpen Source
AI Tools
- 4086AI Tools
Speech recognition model for Chinese, English and dialects that accepts hotwords as context.
Modelhuggingface.coOpen Source
AI Tools
- 744Developer Tools
Packages an LLM's weights with llama.cpp into a single cross-platform executable that runs with no installation.
Runtimehttps://github.com/mozilla-ai/llamafileOpen Source
Developer Tools