#7979th of 81 in VoiceFor voice, speech and music
agnentic-voice-ai-sdk
Kotlin library for voice conversations with Claude in Android apps
- Stars
- 2.6k
- License
- no license
- Last commit
- Jun 2026
- Language
- Kotlin
2,535 on 21 Apr 20262,579 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An Android library that chains microphone capture, voice activity detection, speech-to-text, Anthropic Claude and text-to-speech into one session, configured through a single VoiceAISDK.Builder. It includes Jetpack Compose components such as VoiceButton and ConversationView. STT and TTS engines are swappable (Android built-in, OpenAI Whisper, ElevenLabs), and it has optional PII redaction and emotion detection.
Who it is for: Android developers adding a voice assistant on Claude to their app
Strengths
- Swappable STT and TTS engines behind interfaces: Android built-in, Whisper, ElevenLabs
- Ships Compose UI pieces and a runtime RECORD_AUDIO permission gate
- Optional PII redaction, certificate pinning and encrypted key storage via EncryptedSharedPreferences
- Works without Hilt by building the SDK directly with the Builder
Weaknesses
- Claude is the only AI engine; no local or other LLM provider
- Requires an Anthropic API key and network; default Android STT also needs network
- Android only; the repo is flagged as a template and no release is published
- Tooling detected no license file despite the README's MIT badge and text
What it needs
- Needs Anthropic API key, OpenAI API key (optional, Whisper), ElevenLabs API key (optional), Hume AI API key (optional), Android 7.0+ (minSdk 24)
- Models: Anthropic Claude (default claude-3-5-sonnet-20241022)
Quick answers
Is agnentic-voice-ai-sdk open source?
Its code is public on GitHub, but the repository has no license, so by default nobody may reuse it.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |