Skip to content

Commit 00d4e7c

Browse files
Whats New for the week of 11-2-26: (#1397)
1 parent ae9ad5f commit 00d4e7c

16 files changed

Lines changed: 60 additions & 69 deletions

File tree

‎fern/assistants/examples/voice-widget.mdx‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -382,8 +382,8 @@ const EcommerceSupportWidget = () => {
382382
theme: 'ecommerce',
383383
greeting: 'Hi! Need help with your order?',
384384
voice: {
385-
provider: 'playht',
386-
voiceId: 'jennifer',
385+
provider: 'vapi',
386+
voiceId: 'Elliot',
387387
},
388388
}}
389389
/>
@@ -403,8 +403,8 @@ const HealthcareWidget = () => {
403403
theme: 'healthcare',
404404
greeting: 'Hello! I can help schedule your appointment.',
405405
voice: {
406-
provider: 'playht',
407-
voiceId: 'jennifer',
406+
provider: 'vapi',
407+
voiceId: 'Elliot',
408408
},
409409
}}
410410
/>

‎fern/assistants/structured-outputs.mdx‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -610,6 +610,12 @@ structured_output = vapi.structured_outputs.create(
610610
```
611611
</CodeBlocks>
612612
613+
### Reasoning effort
614+
615+
When extraction runs on an OpenAI reasoning model (the GPT-5 family, GPT-5.6, or GPT-6), set `model.reasoningEffort` to control how much the model reasons before it extracts. Lower it to save cost and latency, or raise it for harder extraction prompts.
616+
617+
Each model accepts only the efforts OpenAI supports for it, for example `none` and `xhigh` on GPT-5.6, or `minimal` on GPT-5. Setting an effort on a non-reasoning model such as GPT-4.1, or on a non-OpenAI model, returns a `400`. When unset, extraction uses the model's current default. Reasoning effort applies to the primary extraction only; the GPT-4.1 fallback runs without it. Reasoning tokens are billed as output tokens.
618+
613619
### Available variables
614620
615621
Use these variables in custom prompts:

‎fern/calls/call-ended-reason.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -139,7 +139,7 @@ Each voice provider has specific error codes. Common patterns:
139139
- `*-unsupported-model` — The voice provider rejected the configured model.
140140
- `*-socket-hang-up` / `*-500-server-error` / `*-503-server-error` — Voice provider infrastructure issue.
141141

142-
**Supported providers:** ElevenLabs, Cartesia, Deepgram, PlayHT, Azure, OpenAI, Rime AI, Smallest AI, Neuphonic, Hume, Sesame, Inworld, Minimax, WellSaid, Custom Voice.
142+
**Supported providers:** ElevenLabs, Cartesia, Deepgram, Azure, OpenAI, Rime AI, Smallest AI, Neuphonic, Hume, Sesame, Inworld, Minimax, WellSaid, Custom Voice.
143143

144144
## Pipeline errors: transcriber (STT)
145145

‎fern/calls/customer-join-timeout.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -131,7 +131,7 @@ Configure `customerJoinTimeoutSeconds` through the Vapi API for both permanent a
131131
const call = await client.calls.createWeb({
132132
assistant: {
133133
model: { provider: "openai", model: "gpt-4.1-mini" },
134-
voice: { provider: "playht", voiceId: "jennifer" },
134+
voice: { provider: "vapi", voiceId: "Elliot" },
135135
customerJoinTimeoutSeconds: 60
136136
}
137137
});

‎fern/changelog/2026-11-02.mdx‎

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
# What's New: Week of November 2, 2026
2+
3+
## New Voices
4+
5+
1. **GPT-Live voices**: Nine new [GPT-Live](/gpt-live/configuration) voices are available: Nuri, Juni, and Flitz (German), Brise and Sillage (French), Nira (Hindi), Harema and Shida (Japanese), and Noeul (Korean). Assistants that don't use a GPT-Live model can no longer be saved with a GPT-Live only voice.
6+
7+
## Features
8+
9+
1. **GPT-Live prompt editor**: The [GPT-Live](/gpt-live/configuration) speaker and reasoner prompts now use the rich text editor, with visual and code views and a fullscreen mode.
10+
2. **Reasoning effort for structured outputs**: You can now set a reasoning effort for [structured outputs](/assistants/structured-outputs#reasoning-effort) that use an OpenAI reasoning model.
11+
3. **Deepgram feedback filter setting**: Set `feedbackFilterEnabled` to false on a [Deepgram](/providers/transcriber/deepgram#feedback-filter) transcriber to keep caller speech that repeats what the assistant just said. It's on by default.
12+
4. **Simulation suite generation API**: You can now draft requirements and generate [simulation suites through the API](/observability/simulations-generate-api) with a private API key.
13+
14+
## Fixes and Improvements
15+
16+
1. **ElevenLabs pronunciation dictionaries**: Calls that use an [ElevenLabs](/providers/voice/elevenlabs) pronunciation dictionary without a pinned version no longer fail. They use the dictionary's latest version.
17+
2. **ElevenLabs silent turns**: When ElevenLabs returns no audio for a turn, the call retries once and then switches to your [fallback voice](/voice-fallback-plan).
18+
3. **GPT-Live phone audio**: [GPT-Live](/gpt-live/configuration) phone calls no longer have short gaps of silence in the middle of words.

‎fern/customization/custom-voices/playht.mdx‎

Lines changed: 0 additions & 42 deletions
This file was deleted.

‎fern/customization/multilingual.mdx‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -491,7 +491,6 @@ Use [plan test coverage](/test/plan-test-coverage) to prioritize the languages a
491491
| **Azure** | 140+ | ✅ Automatic | Maximum language coverage |
492492
| **ElevenLabs** | 30+ | ✅ Automatic | Premium voice quality |
493493
| **OpenAI TTS** | 50+ | ✅ Automatic | Consistent quality across languages |
494-
| **PlayHT** | 80+ | ✅ Automatic | Cost-effective scaling |
495494

496495
## Common challenges and solutions
497496

‎fern/customization/speech-configuration.mdx‎

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,7 @@ description: Control when a Vapi assistant starts and stops speaking, tuning spe
1010
Speech configuration lets you control exactly when your assistant starts and stops speaking during a conversation. By tuning these settings, you can make your assistant feel more natural, avoid interrupting the customer, and reduce awkward pauses.
1111

1212
<Note>
13-
Speech speed can be controlled, but only PlayHT currently supports this
14-
feature with the `speed` field. Other providers do not currently support
15-
speed.
13+
Some voice providers support a `speed` field to control how fast the assistant speaks. Support and the accepted range vary by provider.
1614
</Note>
1715

1816
The two main components are:

‎fern/docs.yml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -258,8 +258,6 @@ navigation:
258258
contents:
259259
- page: Elevenlabs
260260
path: customization/custom-voices/elevenlabs.mdx
261-
- page: PlayHT
262-
path: customization/custom-voices/playht.mdx
263261
- page: Cartesia
264262
path: customization/custom-voices/cartesia.mdx
265263
- page: Gandr
@@ -1183,6 +1181,8 @@ redirects:
11831181
destination: /providers/voice/overview
11841182
- source: /providers/voice/playht
11851183
destination: /providers/voice/overview
1184+
- source: /customization/custom-voices/playht
1185+
destination: /customization/custom-voices/custom-voice
11861186
- source: /providers/voice/sesame
11871187
destination: /providers/voice/overview
11881188
- source: /providers/transcriber/talkscriber

‎fern/gpt-live/configuration.mdx‎

Lines changed: 18 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,7 @@ GPT-Live supports a different set of features from Vapi's other voice architectu
2020
| Browser WebRTC, native Twilio, and Vapi SIP | Supported |
2121
| Raw WebSocket | Supported with mono, signed 16-bit little-endian PCM at 24 kHz. Set the rate explicitly |
2222
| Native Telnyx or Vonage | Not supported |
23-
| 22 preset OpenAI voices | Supported. See [voices](#voices) |
23+
| 31 preset OpenAI voices | Supported. See [voices](#voices) |
2424
| Custom or cloned voices, or other voice providers | Not supported |
2525
| Changing voice during a call | Not supported. Save the assistant and start a new call |
2626
| Model and voice fallbacks | Not supported. GPT-Live also can't be a fallback model |
@@ -161,7 +161,7 @@ Keep delegation triggers in the prompt in the same language. Try names, dates, a
161161

162162
## Voices
163163

164-
Choose any of these 22 voices with `voice.provider: "openai"` and `voice.voiceId`. Save the assistant and start a new call to change voices. In-call voice changes aren't supported.
164+
Choose any of these 31 voices with `voice.provider: "openai"` and `voice.voiceId`. Save the assistant and start a new call to change voices. In-call voice changes aren't supported.
165165

166166
### Voices with regional tags
167167

@@ -197,6 +197,22 @@ Use the tags to narrow your choices, then listen to the samples. Bossa and Tempo
197197
| Shimmer | `shimmer` | [Listen to Shimmer](https://voices-storage.vapi.ai/gpt-live/marble-alpha-v6/shimmer.mp3) |
198198
| Verse | `verse` | [Listen to Verse](https://voices-storage.vapi.ai/gpt-live/marble-alpha-v6/verse.mp3) |
199199

200+
### Additional language voices
201+
202+
These voices speak other languages:
203+
204+
| Voice | API ID | Language |
205+
| --- | --- | --- |
206+
| Nuri | `nuri` | German |
207+
| Juni | `juni` | German |
208+
| Flitz | `flitz` | German |
209+
| Brise | `brise` | French |
210+
| Sillage | `sillage` | French |
211+
| Nira | `nira` | Hindi |
212+
| Harema | `harema` | Japanese |
213+
| Shida | `shida` | Japanese |
214+
| Noeul | `noeul` | Korean |
215+
200216
## Greetings and duration
201217

202218
| Field or feature | Behavior |

0 commit comments

Comments
 (0)