For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
WebsiteStatusSupportDashboard
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
DocumentationAPI ReferenceMCPSDKsCLI (new)What's New?
  • Get started
    • Introduction
    • Phone calls
    • Web calls
    • Vapi Guides
    • Composer
    • CLI quickstart
  • Assistants
    • Quickstart
      • Variables
      • Multilingual support
      • Personalization with user information
      • Voice formatting plan
      • Flush syntax
      • Background messages
      • Idle messages
      • Assistant hooks
      • Background speech denoising
      • Pronunciation dictionaries
      • Email address reading
    • Tools
    • Custom keywords
    • Custom voices
    • Custom transcriber
    • Custom TTS
  • Observability
    • Boards
  • Squads
    • Quickstart
    • Overview
    • Handoff tool
    • Passing data between assistants
  • Best practices
    • Prompting guide
    • Debugging voice agents
    • Enterprise environments (DEV/UAT/PROD)
    • IVR navigation
  • Phone numbers
    • Free Vapi number
    • Inbound SMS
    • Phone Number Hooks
  • Calls
    • Call end reasons
    • Troubleshoot call errors
  • Outbound Campaigns
    • Quickstart
    • Overview
  • Chat
    • Quickstart
    • Streaming
    • Non-streaming
    • OpenAI compatibility
    • Session management
    • Variable substitution
    • SMS chat
    • Web widget
    • Webhooks
  • Workflows
    • Quickstart
    • Overview
LogoLogo
WebsiteStatusSupportDashboard
On this page
  • Overview
  • Configure automatic language detection
  • Set up multilingual voices
  • Configure language-aware prompts
  • Add multilingual greetings
  • Test your multilingual assistant
  • Provider capabilities (Accurate as of testing)
  • Speech Recognition (Transcription)
  • Voice Synthesis (Text-to-Speech)
  • Common challenges and solutions
  • Next steps
AssistantsConversation behavior

Multilingual support

Enable voice assistants to speak multiple languages fluently
Was this page helpful?
Edit this page
Previous

Personalization with user information

Add customer-specific information to your voice assistant conversations

Next
Built with

Overview

Configure your voice assistant to communicate in multiple languages with automatic language detection, native voice quality, and cultural context awareness.

In this guide, you’ll learn to:

  • Set up automatic language detection for speech recognition
  • Configure multilingual voice synthesis
  • Design language-aware system prompts
  • Test and optimize multilingual performance

Multilingual Support: Multiple providers support automatic language detection. Deepgram (Nova 2, Nova 3 with “Multi” setting), Google STT (with “Multilingual” setting), and Gladia (automatic language detection) all offer seamless multilingual conversations.

Configure automatic language detection

Set up your transcriber to automatically detect and process multiple languages.

Dashboard
TypeScript (Server SDK)
Python (Server SDK)
cURL
  1. Navigate to Assistants in your Vapi Dashboard
  2. Create a new assistant or edit an existing one
  3. In the Transcriber section:
    • Provider: Select Deepgram (recommended), Google, or Gladia
    • Model: For Deepgram, choose Nova 2 or Nova 3; for Google, choose Latest; for Gladia, choose Solaria
    • Language / Mode: Set Multi (Deepgram), Multilingual (Google), or choose the language you want to transcribe (Gladia)
  4. Other providers: May require a single languages and not auto-detect
  5. Click Save to apply the configuration

Provider Performance: Deepgram offers the best balance of speed and multilingual accuracy. Google provides broader language support but may be slower. Gladia offers excellent automatic language recognition and code-switching with strong accuracy reported by customers. All three support automatic language detection within conversations.

Set up multilingual voices

Configure your assistant to use appropriate voices for each detected language.

Dashboard
TypeScript (Server SDK)
Python (Server SDK)
cURL
  1. In the Voice section of your assistant:
    • Provider: Select Azure (best multilingual coverage)
    • Voice: Choose multilingual-auto for automatic voice selection
  2. Alternative: Configure specific voices for each language:
    • Select a primary voice (e.g., en-US-AriaNeural)
    • Click Add Fallback Voices
    • Add voices for other languages:
      • Spanish: es-ES-ElviraNeural
      • French: fr-FR-DeniseNeural
      • German: de-DE-KatjaNeural
  3. Click Save to apply the voice configuration

Voice Provider Support: Unlike transcription, all major voice providers (Azure, ElevenLabs, OpenAI, etc.) support multiple languages. Azure offers the most comprehensive coverage with 400+ voices across 140+ languages.

Configure language-aware prompts

Create system prompts that explicitly list supported languages and handle multiple languages gracefully.

Dashboard
TypeScript (Server SDK)
Python (Server SDK)
cURL
  1. In the Model section, update your system prompt to explicitly list supported languages:
You are a helpful assistant that can communicate in English, Spanish, and French.
Language Instructions:
- You can speak and understand: English, Spanish, and French
- Automatically detect and respond in the user's language
- Switch languages seamlessly when the user changes languages
- Maintain consistent personality across all languages
- Use culturally appropriate greetings and formality levels
If a user speaks a language other than English, Spanish, or French, politely explain that you only support these three languages and ask them to continue in one of them.
  1. Click Save to apply the prompt changes

Critical for Multilingual Success: You must explicitly list the supported languages in your system prompt. Assistants struggle to understand they can speak multiple languages without this explicit instruction.

Add multilingual greetings

Configure greeting messages that work across multiple languages.

Dashboard
TypeScript (Server SDK)
Python (Server SDK)
cURL
  1. In the First Message field, enter a multilingual greeting:
Hello! I can assist you in English, Spanish, or French. How can I help you today?
  1. Optional: For more personalized greetings, use the Advanced Message Configuration:
    • Enable Language-Specific Messages
    • Add greetings for each target language
  2. Click Save to apply the greeting

Test your multilingual assistant

Validate your configuration with different languages and scenarios.

Dashboard
TypeScript (Server SDK)
Python (Server SDK)
cURL
  1. Use the Test Assistant feature in your dashboard
  2. Test these scenarios:
    • Start conversations in different languages
    • Switch languages mid-conversation
    • Use mixed-language input
  3. Monitor the Call Analytics for:
    • Language detection accuracy
    • Voice quality consistency
    • Response appropriateness
  4. Adjust configuration based on test results

Provider capabilities (Accurate as of testing)

Speech Recognition (Transcription)

ProviderMultilingual SupportLanguagesNotes
Deepgram✅ Full auto-detection100+Recommended: Nova 2/Nova 3 with “Multi” language setting
Google STT✅ Full auto-detection125+Latest models with “Multilingual” language setting
Gladia✅ Full auto-detection110+Supports automatic language detection and code-switching
Assembly AI❌ English onlyEnglishNo multilingual support
Azure STT❌ Single language100+Many languages, but no auto-detection
OpenAI Whisper❌ Single language90+Many languages, but no auto-detection
Speechmatics❌ Single language50+Many languages, but no auto-detection
Talkscriber❌ Single language40+Many languages, but no auto-detection

Voice Synthesis (Text-to-Speech)

ProviderLanguagesMultilingual Voice SelectionBest For
Azure140+✅ AutomaticMaximum language coverage
ElevenLabs30+✅ AutomaticPremium voice quality
OpenAI TTS50+✅ AutomaticConsistent quality across languages
PlayHT80+✅ AutomaticCost-effective scaling

Common challenges and solutions

Language detection is inaccurate

Solutions:

  • Use Deepgram (Nova 2/Nova 3 with “Multi”), Google STT (with “Multilingual”), or Gladia (automatic language detection)
  • Ensure high-quality audio input for better detection accuracy
  • Test with native speakers of target languages
  • Consider provider-specific language combinations for optimal results
Assistant doesn't realize it can speak multiple languages

Solutions:

  • Explicitly list all supported languages in your system prompt
  • Include language capabilities in the assistant’s instructions
  • Test the prompt with multilingual conversations
  • Avoid generic “multilingual” statements without specifics
Transcription is too slow

Solutions:

  • Use Deepgram Nova 2/Nova 3 for optimal speed and multilingual support
  • For Google STT, use latest models for better performance
  • Consider the speed vs accuracy tradeoff for your use case
  • Optimize audio quality and format to improve processing speed
Voice quality varies between languages

Solutions:

  • Test different voice providers for each language
  • Use Azure for maximum language coverage
  • Configure fallback voices as backup options
  • Consider premium providers for key languages

Next steps

Now that you have multilingual support configured:

  • Build a complete multilingual agent: Follow our step-by-step implementation guide
  • Custom voices: Set up region-specific custom voices
  • System prompting: Design effective multilingual prompts
  • Call analysis: Monitor language performance and usage