Skip to content
Back to search

aru-voice-call

Real-time voice call for AI companions — talk to your AI like a phone call. Supports emotion detection, real-time transcription, and ElevenLabs TTS. Works as MCP server for Aru integration.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/brittanyyy77--aru-voice-call/badge.svg)](/listings/brittanyyy77--aru-voice-call)

HTML

<a href="/listings/brittanyyy77--aru-voice-call"><img src="/api/listings/brittanyyy77--aru-voice-call/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Clone and configure

git clone https://github.com/brittanyyy77/aru-voice-call.git
cd aru-voice-call
cp .env.example .env
# Edit .env with your API keys

2. Run with Docker

docker compose up -d

3. Open in browser

Go to `https://your-vps-ip:8443` on your phone.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 119 lines
  1. # aru-voice-call
  2. Real-time voice call for AI companions — talk to your AI like a phone call.
  3. ## Features
  4. - 🎙️ Real-time voice transcription (cloud or local)
  5. - 🎭 Emotion detection from voice (pitch, speed, volume, pauses)
  6. - 🔊 AI voice reply via ElevenLabs or MiniMax TTS
  7. - 📱 Works on mobile browsers, no app needed
  8. - 🐳 One-command Docker deployment
  9. - 🌏 China-friendly: supports Aliyun, Volcengine, Baidu STT + MiniMax TTS
  10. - 🔌 Optional MCP server for Aru integration
  11. ## How It Works
  12. The entire call loop runs autonomously on your VPS:
  13. ```
  14. You speak → Browser captures audio
  15. → WebSocket streams to VPS
  16. → STT transcribes (cloud API or local whisper)
  17. → librosa analyzes emotion
  18. → LLM generates reply (with emotion context)
  19. → TTS synthesizes voice (ElevenLabs or MiniMax)
  20. → Audio streams back to your browser
  21. → You hear the reply
  22. ```
  23. **No MCP needed for the call itself.** Fully real-time, no middleware delay.
  24. ## Quick Start
  25. ### 1. Clone and configure
  26. ```bash
  27. git clone https://github.com/brittanyyy77/aru-voice-call.git
  28. cd aru-voice-call
  29. cp .env.example .env
  30. # Edit .env with your API keys
  31. ```
  32. ### 2. Run with Docker
  33. ```bash
  34. docker compose up -d
  35. ```
  36. ### 3. Open in browser
  37. Go to `https://your-vps-ip:8443` on your phone.
  38. ## Providers
  39. ### Speech-to-Text (STT)
  40. | Provider | Region | Free Tier | Config |
  41. |----------|--------|-----------|--------|
  42. | Groq | International | Yes | `STT_PROVIDER=groq` |
  43. | Deepgram | International | Yes | `STT_PROVIDER=deepgram` |
  44. | Aliyun | China | Pay-as-you-go | `STT_PROVIDER=aliyun` + `STT_APPKEY` |
  45. | Volcengine | China | Free quota | `STT_PROVIDER=volcengine` + `STT_APPID` |
  46. | Baidu | China | Free quota | `STT_PROVIDER=baidu` |
  47. | Local Whisper | Any | Free (CPU/GPU) | `STT_MODE=local` |
  48. ### Text-to-Speech (TTS)
  49. | Provider | Region | Config |
  50. |----------|--------|--------|
  51. | ElevenLabs | International | `TTS_PROVIDER=elevenlabs` |
  52. | MiniMax | China | `TTS_PROVIDER=minimax` |
  53. ## Configuration
  54. See `.env.example` for all options. Key settings:
  55. ```env
  56. # International setup
  57. STT_PROVIDER=groq
  58. TTS_PROVIDER=elevenlabs
  59. # China setup (no foreign card needed)
  60. STT_PROVIDER=volcengine
  61. TTS_PROVIDER=minimax
  62. ```
  63. ### SSL Certificate
  64. Mobile browsers require HTTPS for microphone access:
  65. ```bash
  66. mkdir certs
  67. # Copy your fullchain.pem and privkey.pem into certs/
  68. ```
  69. ## Optional: Aru MCP Integration
  70. If you use [Aru](https://aru.app), bind this as an MCP server:
  71. - URL: `https://your-vps:8443/mcp`
  72. - Transport: `streamable-http`
  73. MCP tools:
  74. - `get_call_status` — Check active/completed calls
  75. - `get_call_transcript` — Get full transcript with emotions after call
  76. - `push_message` — Say something into an active call
  77. - `get_live_emotion` — Check user's mood during call
  78. ## Tech Stack
  79. - **Backend**: Python, FastAPI, WebSocket
  80. - **STT**: Groq / Deepgram / Aliyun / Volcengine / Baidu / local whisper
  81. - **Emotion**: librosa audio feature extraction
  82. - **TTS**: ElevenLabs / MiniMax streaming
  83. - **Frontend**: Vanilla HTML/JS, Web Audio API
  84. - **Deploy**: Docker Compose
  85. ## License
  86. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.