> ## Documentation Index > Fetch the complete documentation index at: https://docs.callintel.io/llms.txt > Use this file to discover all available pages before exploring further. # Speech-to-Text Integration > Configure AssemblyAI, Deepgram, and Cartesia for voice input. Speech-to-Text providers convert customer voice into text for processing. This guide covers available providers and setup. ## Available Providers ### Deepgram (Recommended - Best Performance) **Why Choose Deepgram:** * Lowest latency (200ms) * Highest accuracy * Excellent cost/performance ratio * Best for real-time conversations Latency: \< 200ms (fastest) Accuracy: 95%+ Cost: \~0.0043 USD per minute Languages: 40+ ### AssemblyAI (Best for Accuracy) **Why Choose AssemblyAI:** * Exceptional accuracy * Great documentation * Reliable service * Good cost structure Latency: 200-400ms Accuracy: 95%+ Cost: \~0.0075 USD per minute Languages: 99+ Special Features: Speaker diarization, entity detection ### Cartesia (Enterprise Grade) **Why Choose Cartesia:** * Enterprise-level performance * Custom models available * Premium support * Dedicated infrastructure **Specifications:** * Latency: \< 250ms * Accuracy: 96%+ * Cost: Custom pricing * Languages: 40+ * Special Features: Domain adaptation, custom models ## Provider Comparison | Feature | Deepgram | AssemblyAI | Cartesia | | --------- | -------- | ---------- | -------- | | Latency | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | | Accuracy | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | | Cost | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐ | | Languages | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | | Support | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ## Setup ### Deepgram Setup (Recommended) **Step 1: Create Account** 1. Visit [deepgram.com](https://console.deepgram.com/signup) 2. Sign up for free account 3. Verify email **Step 2: Get API Key** 1. Go to Console 2. Click "API Keys" in left menu 3. Click "Create a new API Key" 4. Select "Scoped API Key" 5. Assign "speech-to-text" scope 6. Copy key **Step 3: Add to CallIntel** 1. Go to Settings → Developer Settings 2. Click "API Keys" 3. Select "Deepgram" from provider list 4. Paste API key 5. Click "Test Connection" 6. Save **Step 4: Configure Agent** 1. Create/Edit Agent 2. Under "Speech-to-Text", select: * `nova-2` (default, best accuracy) * `nova` (faster) * `enhanced` (most accurate) 3. Select language and options 4. Save ### AssemblyAI Setup **Step 1: Create Account** 1. Visit [assemblyai.com](https://www.assemblyai.com) 2. Sign up for account 3. Verify email **Step 2: Get API Key** 1. Go to Dashboard 2. Click "API Keys" in sidebar 3. Copy API key under "Your API Token" **Step 3: Add to CallIntel** 1. Go to Settings → Developer Settings 2. Click "API Keys" 3. Select "AssemblyAI" from provider list 4. Paste API key 5. Click "Test Connection" 6. Save **Step 4: Configure Agent** 1. Create/Edit Agent 2. Under "Speech-to-Text", select: * "Standard" (default) * "Enhanced" (more accurate) 3. Configure language 4. Enable diarization if needed 5. Save ### Cartesia Setup **Step 1: Contact Sales** 1. Visit [cartesia.ai](https://cartesia.ai) 2. Request enterprise access 3. Complete onboarding 4. Receive API credentials **Step 2: Get API Key** Cartesia provides during onboarding. **Step 3: Add to CallIntel** 1. Go to Settings → Developer Settings 2. Click "API Keys" 3. Select "Cartesia" from provider list 4. Paste API key 5. Click "Test Connection" 6. Save **Step 4: Configure Agent** 1. Create/Edit Agent 2. Under "Speech-to-Text", select Cartesia 3. Configure custom model (if provided) 4. Set language and options 5. Save ## Cost Comparison ### Monthly Costs (1000 calls, 2 min avg) **Cost Example (1000 calls/month):** Deepgram: * 1000 calls × 2 minutes = 2000 minutes * 2000 × 0.0043 USD = 8.60 USD/month * Cost per call: 0.0086 USD AssemblyAI: * 1000 calls × 2 minutes = 2000 minutes * 2000 × 0.0075 USD = 15 USD/month * Cost per call: 0.015 USD Cartesia: * Custom pricing (typically 5000-10000 USD/month for enterprise) **Recommendation**: Use Deepgram for cost-optimal performance. ## Language Support ### Deepgram Languages ``` English (US, UK, Australia, India, New Zealand) Spanish, French, German, Italian, Dutch, Russian Portuguese, Mandarin, Cantonese, Korean, Japanese Arabic, Hindi, and 20+ more ``` **Configure in Agent:** ``` 1. Edit Agent 2. Under STT, select language 3. Use language codes: - en (English) - es (Spanish) - fr (French) - de (German) - etc. 4. Save ``` ### AssemblyAI Languages AssemblyAI supports 99 languages with automatic detection. **Auto-Detection:** ``` 1. Set language to "Auto" 2. System detects language automatically 3. Great for multilingual operations ``` ## Configuration Options ### Model Selection #### Deepgram Models **Nova 2** (Default) ``` Best For: Most use cases Accuracy: Highest Speed: Fast Cost: Standard Recommended: YES ✓ ``` **Nova** ``` Best For: Budget-conscious Accuracy: Excellent Speed: Very Fast Cost: Standard ``` **Enhanced** ``` Best For: Noisy environments Accuracy: Very High Speed: Standard Cost: Standard ``` #### Key Configuration Options **Punctuation** ``` Enabled: Add punctuation to transcripts Disabled: Raw text without punctuation Default: Enabled Recommendation: Enable for better readability ``` **Profanity Filter** ``` Enabled: Replace profanity with [profanity] Disabled: Include all words Default: Disabled Recommendation: Enable for customer interactions ``` **Number Conversion** ``` Enabled: Convert "one" to "1" Disabled: Keep as written text Default: Enabled Recommendation: Enable for phone numbers, quantities ``` **Speaker Diarization** (AssemblyAI) ``` Enabled: Identify different speakers Disabled: Single speaker transcript Cost: Additional (check pricing) Recommendation: Enable for multi-party calls ``` ## Advanced Features ### Real-Time Transcription Get transcripts as customer speaks: ``` Advantage: Immediate feedback Use Case: Live coaching, monitoring Cost: Higher (streaming mode) Latency: 200-500ms ``` ### Accuracy Enhancements **Boost Accuracy:** 1. Provide domain vocabulary 2. Add expected phrases 3. Use correct language setting 4. Choose higher-accuracy model **Example:** ``` Your company: "Acme Corp" Products: "WidgetPro", "GadgetMax" Add to STT configuration Result: Better recognition of custom terms ``` ### Sentiment Analysis Available through some providers: ``` Sentiment Detection: - Positive, Negative, Neutral - Confidence score - Available in: AssemblyAI ``` ## Troubleshooting Try: Deepgram Nova 2 (best accuracy), AssemblyAI Enhanced model, or add domain vocabulary. Switch to Deepgram (lowest latency). Check internet connection quality. Monitor actual usage in provider dashboard. Consider switching to Deepgram for better pricing. Ensure correct language is selected. Some providers need explicit language configuration. Verify key is correct, not expired, and has correct permissions. Regenerate key in provider dashboard. ## Best Practices ### 1. Start with Deepgram Nova 2 ``` Best balance of: - Accuracy (highest) - Speed (fast) - Cost (competitive) - Languages (40+) ``` ### 2. Monitor Accuracy ``` Weekly Review: - Sample 10 calls - Check transcript accuracy - Note problem phrases - Adjust configuration if needed ``` ### 3. Use Language Setting ``` Always specify language explicitly Auto-detection works but is slower Specified language: 5-10ms faster ``` ### 4. Enable Helpful Features ``` ✓ Enable: Punctuation (readability) ✓ Enable: Number conversion (clarity) ✓ Consider: Profanity filter (compliance) ✓ Consider: Diarization (if multi-party) ``` ## Performance Tips ### Optimize Response Time ``` Action | Impact | Recommendation ---------------------|-----------|---------------- Lower-latency model | Critical | Deepgram Nova 2 Specify language | ~10ms | Always specify Enable streaming | 200-300ms | Default in CallIntel Reduce audio quality | -5ms | Not recommended ``` ### Monitor Quality Create dashboards for: ``` - Transcription accuracy % - Processing latency (ms) - Cost per minute - Language breakdown - Error rate ``` ## See Also Configure voice output Identify different speakers Configure complete agents *** ## Support [Deepgram Documentation](https://developers.deepgram.com) [AssemblyAI Documentation](https://www.assemblyai.com/docs) Email: [callintel01@gmail.com](mailto:callintel01@gmail.com)