|
| 1 | +## Enhanced Voicemail Detection, File Processing, Knowledge Base Integration, and Invoicing Updates |
| 2 | + |
| 3 | +1. **Track Voicemail Detection Cost, Configure Google and Twilio Voicemail Detection Plans** |
| 4 | + |
| 5 | +* You can now configure provider-specific settings and track voicemail detection costs through the new `VoicemailDetectionCost` schema at `call.costs[type=voicemail-detection]`. |
| 6 | +* Configure Google or Twilio voicemail detection settings using the new [`GoogleVoicemailDetectionPlan`](https://api.vapi.ai/api#:~:text=GoogleVoicemailDetectionPlan) and [`TwilioVoicemailDetectionPlan`](https://api.vapi.ai/api#:~:text=TwilioVoicemailDetectionPlan) schemas. |
| 7 | + |
| 8 | +```json |
| 9 | +// Google configuration example |
| 10 | +{ |
| 11 | + "provider": "google", |
| 12 | + "voicemailExpectedDurationSeconds": 15 // Range: 5-60 seconds |
| 13 | +} |
| 14 | +``` |
| 15 | + |
| 16 | +```json |
| 17 | +// Twilio configuration example |
| 18 | +{ |
| 19 | + "provider": "twilio", |
| 20 | + "enabled": true, |
| 21 | + "machineDetectionTimeout": 30, // Range: 3-59 seconds |
| 22 | + "voicemailDetectionTypes": ["machine_end_beep", "machine_end_silence"] |
| 23 | +} |
| 24 | +``` |
| 25 | + |
| 26 | +2. **Improved File Processing Statuses and Parsed Text Content** |
| 27 | + |
| 28 | +* File processing statuses have been renamed to better reflect their purpose: `processing` → `done` → `failed`. |
| 29 | +* Two new properties have been added to the [`File`](https://api.vapi.ai/api#:~:text=File) schema: `parsedTextUrl` and `parsedTextBytes`, providing direct access to parsed text content from processed files. |
| 30 | + |
| 31 | +3. **Google Gemini Models for Knowledge Base Integration** |
| 32 | + |
| 33 | +* The [`KnowledgeBase`](https://api.vapi.ai/api#:~:text=KnowledgeBase) schema now fully supports Google's Gemini models with specific model options. |
| 34 | +* You can use Gemini models in your knowledge bases at `assistant.model.tools[type=query].knowledgeBases`. |
| 35 | + |
| 36 | +```json |
| 37 | +"model": { |
| 38 | + "enum": [ |
| 39 | + "gemini-2.0-flash-thinking-exp", |
| 40 | + "gemini-2.0-pro-exp-02-05", |
| 41 | + "gemini-2.0-flash", |
| 42 | + "gemini-2.0-flash-lite-preview-02-05", |
| 43 | + "gemini-2.0-flash-exp", |
| 44 | + "gemini-2.0-flash-realtime-exp", |
| 45 | + "gemini-1.5-flash", |
| 46 | + "gemini-1.5-flash-002", |
| 47 | + "gemini-1.5-pro", |
| 48 | + "gemini-1.5-pro-002", |
| 49 | + "gemini-1.0-pro" |
| 50 | + ] |
| 51 | +} |
| 52 | +``` |
| 53 | + |
| 54 | +4. **New Invoicing Features** |
| 55 | + |
| 56 | +* You can now use [`InvoicePlan`](https://api.vapi.ai/api#:~:text=InvoicePlan) schema for customizing invoice information with company details. |
| 57 | +* This can be accessed via the new `invoicePlan` property on the [`Subscription`](https://api.vapi.ai/api#:~:text=Subscription) schema. |
| 58 | +* Customize company name, email, tax ID, and address for your invoices. |
| 59 | + |
| 60 | +5. **Additional Voice Options** |
| 61 | + |
| 62 | +* Five new voice options have been added to the [`FallbackVapiVoice`](https://api.vapi.ai/api#:~:text=FallbackVapiVoice) schema: `Adi`, `Julia`, `Maibri (Web)`, `Maibri (Phone)`, and `Ashley`. |
| 63 | +* Configure these voices in your assistant fallback plans at `assistant.voice.fallbackPlan.voices`. |
| 64 | +<Frame caption="Additional Vapi Voices"> |
| 65 | + <img src="../static/images/changelog/additional-vapi-voices.png" alt="Additional Vapi Voices" /> |
| 66 | +</Frame> |
0 commit comments