Changelog

Get the (almost) daily changelog

New Workflows API, Telnyx Phone Number Support, Voice Options, and much more

  1. Workflows Replace Blocks: The API has migrated from blocks to workflows with new /workflow endpoints. Introduction to Workflows You can now use UpdateWorkflowDTO where conversation components (Say, Gather, ApiRequest, Hangup, Transfer nodes) are explicitly connected via edges to create directed conversation flows.
1{
2 "name": "Customer Support Workflow",
3 "nodes": [
4 {
5 "id": "greeting",
6 "type": "Say",
7 "text": "Hello, welcome to customer support. Do you need help with billing or technical issues?"
8 },
9 {
10 "id": "menu",
11 "type": "Gather",
12 "options": ["billing", "technical", "other"]
13 },
14 {
15 "id": "billing",
16 "type": "Say",
17 "text": "I'll connect you with our billing department."
18 },
19 {
20 "id": "technical",
21 "type": "Say",
22 "text": "I'll connect you with our technical support team."
23 },
24 {
25 "id": "transfer_billing",
26 "type": "Transfer",
27 "destination": {
28 "type": "number",
29 "number": "+1234567890"
30 }
31 },
32 {
33 "id": "transfer_technical",
34 "type": "Transfer",
35 "destination": {
36 "type": "number",
37 "number": "+1987654321"
38 }
39 }
40 ],
41 "edges": [
42 {
43 "from": "greeting",
44 "to": "menu"
45 },
46 {
47 "from": "menu",
48 "to": "billing",
49 "condition": {
50 "type": "logic",
51 "liquid": "{% if input == 'billing' %} true {% endif %}"
52 }
53 },
54 {
55 "from": "menu",
56 "to": "technical",
57 "condition": {
58 "type": "logic",
59 "liquid": "{% if input == 'technical' %} true {% endif %}"
60 }
61 },
62 {
63 "from": "billing",
64 "to": "transfer_billing"
65 },
66 {
67 "from": "technical",
68 "to": "transfer_technical"
69 }
70 ]
71}
  1. Telnyx Phone Number Support: Telnyx is now available as a phone number provider alongside Twilio and Vonage.

  2. New Voice Options:

    • Vapi Voices: New Vapi voices - Elliot, Rohan, Lily, Savannah, and Hana
    • Hume Voice: New provider with octave model and customizable voice settings
    • Neuphonic Voice: New provider with neu_hq (higher quality) and neu_fast (faster) models
  3. New Cerebras Model: CerebrasModel Supports llama3.1-8b and llama-3.3-70b models

  4. Enhanced Transcription:

    • New Providers: ElevenLabs and Speechmatics transcribers now available.
    • DeepgramTranscriber Numerals: New numerals option converts spoken numbers to digits (e.g., “nine-seven-two” → “972”)
  5. Improved Voicemail Detection: You can now use multiple provider implementations for assistant.voicemailDetection (Google, OpenAI, Twilio). OpenAI implementation allows configuring detection duration (5-60 seconds, default: 15).

  6. Smart Endpointing Upgrade: Now supports LiveKit as an alternative to Vapi’s custom-trained model in StartSpeakingPlan.smartEndpointingEnabled. LiveKit only supports English but may offer different endpointing characteristics.

  7. Observability with Langfuse: New assistant.observabilityPlan property allows integration with Langfuse for tracing and monitoring of assistant calls. Configure with LangfuseObservabilityPlan.

  8. More Credential Support: Added support for Cerebras, Google, Hume, InflectionAI, Mistral, Trieve, and Neuphonic credentials in assistant.credentials