Configure how your agent sounds. Choose a TTS provider, select a voice, and adjust speed. What you’ll learn: Provider selection, voice configuration, speed settings, and troubleshooting. Prerequisites: An agent created in Dasha BlackBox. See Create Your First Agent if you haven’t set one up yet.Documentation Index
Fetch the complete documentation index at: https://docs.blackbox.dasha.ai/llms.txt
Use this file to discover all available pages before exploring further.
Default voice: New agents use ElevenLabs Flash V2.5. Change voices anytime without affecting existing calls.
Overview
| Component | What it does | Configuration |
|---|---|---|
| Text-to-Speech (TTS) | Converts agent responses to speech | Manual — choose provider, voice, speed |
| Speech-to-Text (STT) | Transcribes user speech to text | Automatic — platform selects optimal provider |
Provider comparison
| Provider | Best for | Speed range |
|---|---|---|
| ElevenLabs | Natural quality, customization | 0.70x–1.20x |
| Cartesia | Emotions, wide speed range | 0x–2.0x |
| Inworld | Character voices, gaming | 0.80x–1.50x |
| LMNT | Consistent, lightweight | Fixed 1.0x |
Configure voice
Speed settings
| Speed | Use case |
|---|---|
| 0.7x–0.9x | Accessibility, complex information, legal disclosures |
| 1.0x | General conversation, customer support |
| 1.1x–1.5x | Time-sensitive scenarios, experienced users |
Basic configuration
API example: TTS configuration
API example: TTS configuration
Troubleshooting
| Issue | Solution |
|---|---|
| Voice sounds robotic | Try different voice or switch to ElevenLabs |
| Speech too fast/slow | Adjust speed in 0.05x increments |
| Pronunciation errors | Configure pronunciation dictionary via API |
Next steps
TTS providers
Detailed provider configuration
Dashboard Testing
Test voice quality in the browser