talk-buddy

Text-to-Speech Setup

Configure voice synthesis services to enable AI voice responses in Talk Buddy. This guide covers both online and local TTS (Text-to-Speech) service options for natural-sounding conversation practice.

Understanding TTS Services

What is Text-to-Speech?

TTS services convert AI text responses into spoken voice output:

Service Options

Online Services (Default)

Pre-configured services: Ready to use immediately

Self-hosted services: Run on your own computer

Quick Start (Online Services)

Default Configuration

Talk Buddy comes pre-configured with working TTS services:

Check Current Status

  1. Look at status footer: Voice indicator should be green (●)
  2. If green: You’re ready for voice-enabled practice
  3. If red/gray: Follow troubleshooting steps below

Test Voice Service

  1. Go to Settings: Click “Settings” in sidebar
  2. Open the Voice tab: Look for voice synthesis configuration
  3. Click “Test Voice”: Verify service is working
  4. Listen for voice: Should hear test speech output
  5. Check audio quality: Verify voice is clear and understandable

Troubleshooting Online Services

Connection Issues

Audio Problems

Local TTS Setup (Speaches)

Why Use Local Services?

Privacy benefits:

Performance benefits:

Installing Speaches

System Requirements

Installation Steps

Option 1: Docker Installation (Recommended)

# Pull the Speaches Docker image
docker pull ghcr.io/tts-ai/speaches:latest

# Run Speaches container with TTS enabled
docker run -d \
  --name speaches \
  -p 8000:8000 \
  ghcr.io/tts-ai/speaches:latest

Option 2: Python Installation

# Install Python 3.8+ if not already installed
python --version

# Install Speaches via pip
pip install speaches

# Start Speaches server with TTS
speaches serve --host 0.0.0.0 --port 8000 --enable-tts

Option 3: Binary Installation

  1. Download: Get binary from Speaches releases
  2. Extract: Unzip to preferred location
  3. Run: Execute the binary to start server
  4. Configure: Set to run on port 8000 with TTS enabled

Configuring Talk Buddy for Local Voice Synthesis

Update Service URL

  1. Open Talk Buddy Settings
  2. Go to the Voice tab
  3. Find the Service URL field
  4. Change to local address: http://localhost:8000
  5. Save settings

Test Local Connection

  1. Click “Test Voice” in settings
  2. Verify connection: Should show successful connection
  3. Test voice synthesis: Should hear test speech
  4. Check status footer: Voice indicator should be green

Speaches Voice Configuration

Voice Model Selection

Speaches supports multiple voice models:

Fast Models (Lower quality, faster synthesis)

High-Quality Models (Better voices, slower synthesis)

Voice Characteristics

Configure different voices for scenarios:

# Example: Configure female voice
speaches serve --tts-voice "en_US-amy-medium" --port 8000

# Example: Configure male voice
speaches serve --tts-voice "en_US-ryan-high" --port 8000

Language Configuration

Set up for your language:

# Example: Configure for Spanish TTS
speaches serve --tts-language es --tts-voice "es_ES-marta-medium" --port 8000

# Example: Configure for French TTS
speaches serve --tts-language fr --tts-voice "fr_FR-siwis-medium" --port 8000

Advanced TTS Configuration

Create configuration file speaches.yaml:

server:
  host: "0.0.0.0"
  port: 8000
  
stt:
  enabled: true
  model: "Systran/faster-whisper-medium"
  
tts:
  enabled: true
  model: "speaches-ai/piper-en_US-lessac-medium"
  voice_speed: 1.0
  voice_pitch: 0.0
  output_format: "wav"

Advanced TTS Configuration

Multiple Voice Setup

Character-Specific Voices

Configure different voices for different AI characters:

  1. Interview scenarios: Professional, clear voice
  2. Customer service: Friendly, approachable voice
  3. Technical scenarios: Authoritative, confident voice
  4. Casual conversation: Relaxed, conversational voice

Voice Switching

In Talk Buddy settings (Voice tab):

Performance Optimization

Hardware Optimization

For better local TTS performance:

Voice Quality vs Speed

Choose appropriate balance:

Security and Privacy

Local Service Security

Secure your local installation:

Data Privacy

Understand data handling:

Troubleshooting TTS Issues

Common Problems

No Audio Output

Symptoms: Silent AI responses, no voice heard Solutions:

  1. Check system volume: Verify computer audio not muted
  2. Test audio device: Confirm speakers/headphones work with other apps
  3. Check TTS service: Verify service is running and connected
  4. Test different voice: Try alternative voice models

Poor Voice Quality

Symptoms: Robotic voice, audio artifacts, unclear speech Solutions:

  1. Try different voice model: Some models sound more natural
  2. Check audio settings: Verify sample rate and format settings
  3. Update audio drivers: Ensure latest audio drivers installed
  4. Reduce system load: Close other applications using audio

Service Connection Errors

Symptoms: Red Voice indicator, connection timeouts Solutions:

  1. Verify service running: Check if Speaches or online service is available
  2. Test network connectivity: Ensure internet access for online services
  3. Check firewall: Confirm Talk Buddy can access the voice synthesis service
  4. Restart services: Stop and start the voice service, restart Talk Buddy

Slow Voice Generation

Symptoms: Long delays between AI text and voice output Solutions:

  1. Use faster models: Switch to smaller, quicker voice models (Voice tab in Settings)
  2. Optimize hardware: Close other applications, upgrade hardware
  3. Check network: Ensure stable, fast internet for online services
  4. Local processing: Switch to the Built-in (offline) option in the Voice tab for better performance

Advanced Troubleshooting

Log Analysis

Check service logs for errors:

# View Speaches logs
docker logs speaches

# Check system audio logs (macOS)
log show --predicate 'subsystem == "com.apple.coreaudio"' --last 5m

# Windows audio troubleshooting
# Use Windows Audio troubleshooter in Settings

Network Diagnostics

Test service connectivity:

# Test local Speaches service
curl http://localhost:8000/health

# Test TTS endpoint
curl -X POST http://localhost:8000/tts \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, this is a test", "voice": "en_US-amy-medium"}'

Performance Monitoring

Monitor resource usage:

Service Comparison

Online vs Local TTS

Aspect Online Services Local Services
Setup Ready immediately Requires installation
Privacy Data sent externally Complete privacy
Voice Quality Often excellent Varies by model
Speed Network dependent Hardware dependent
Cost May have usage limits Free after setup
Offline Requires internet Works offline
Voices Many options Depends on models

For Students

For Teachers

For Professionals

Quick Setup Checklist

Online Voice Synthesis (5 minutes)

Local Voice Synthesis / Built-in (offline) (45 minutes)

Troubleshooting (15 minutes)

With proper voice setup, your Talk Buddy conversations become immersive and natural. Choose the option that best fits your privacy needs and desired voice quality!

Related Guides:

This site is open source. Improve this page.