latest

Author: chdeskur

fern/api-reference/text-to-speech.mdx

@@ -0,0 +1,172 @@
+---
+title: Text to Speech API Reference
+---
+
+## Why Choose ElevenLabs?
+
+Our AI model produces the highest-quality voices in the industry.
+
+<Card title="Premium Voice Quality">
+  <img src="https://fern-image-hosting.s3.us-east-1.amazonaws.com/elevenlabs/voices.webp" alt="Premium Voice Quality" />
+  
+  Chooose from over **3,000** voices or clone your own. Our industry-leading
+  voice technology delivers the most natural-sounding AI conversations.
+</Card>
+<Card title="32 Languages" horizontal="true">
+  Choose from over 32 languages with 1000s of voices, for every use-case, at
+  192kbps
+</Card>
+<Card title="Ultra-low latency" horizontal>
+  As low as ~250ms (+ network latency) audio generation times with our Turbo
+  model.
+</Card>
+<Card title="Natural Prosody" horizontal>
+  Understands natural speech patterns for lifelike rhythm and intonation.
+</Card>
+
+#### Concurrent Request Limits
+
+The maximum number of concurrent requests you can run in parallel depends on your subscription tier.
+
+<Note>
+  The concurrent request limits don't apply to enterprise tier. [Talk to
+  sales](https://elevenlabs.io/contact-sales) to discuss a custom plan.
+</Note>
+
+<CardGroup cols={2}>
+  <Card title="Free & Starter" horizontal>
+
+    **Free:** 2 concurrent requests
+    
+    **Starter:** 3 concurrent requests
+
+  </Card>
+  <Card title="Creator & Pro" horizontal>
+
+    **Creator:** 5 concurrent requests
+    
+    **Pro:** 10 concurrent requests
+
+  </Card>
+  <Card title="Scale & Business" horizontal>
+
+    **Scale:** 15 concurrent requests
+    
+    **Business:** 15 concurrent requests
+
+  </Card>
+  <Card title="Enterprise" horizontal href="https://elevenlabs.io/contact-sales">
+
+    Need higher limits? **[Talk to sales](https://elevenlabs.io/contact-sales)**
+
+  </Card>
+</CardGroup>
+
+### Supported Languages
+
+Our TTS API is multilingual and currently supports 32 languages across multiple regions.
+
+<CardGroup cols={3}>
+  <Card title="Asia & Pacific" horizontal>
+
+    Chinese
+    
+    Japanese
+    
+    Korean
+    
+    Vietnamese
+    
+    Filipino
+    
+    Indonesian
+    
+    Malay 
+    
+    Tamil
+    
+    Hindi
+
+  </Card>
+  <Card title="Europe (West)" horizontal>
+
+    English
+    
+    French
+    
+    German
+    
+    Italian
+    
+    Spanish
+    
+    Dutch
+    
+    Portuguese  
+    
+    Norwegian
+    
+    Swedish
+    
+    Danish
+
+  </Card>
+  <Card title="Europe (East)" horizontal>
+
+    Polish
+    
+    Ukrainian
+    
+    Russian
+    
+    Czech
+    
+    Slovak
+    
+    Romanian
+    
+    Bulgarian
+    
+    Croatian
+    
+    Greek
+    
+    Hungarian
+    
+    Finnish
+    
+    Turkish
+    
+    Classic Arabic
+
+  </Card>
+</CardGroup>
+
+To use any of these languages, simply provide the input text in your language of choice.
+
+<CardGroup cols={2}>
+  <Card
+    title="Streaming API"
+    icon="regular book-open-cover"
+    href="/api-reference/streaming"
+  >
+    Dig into the details of using the ElevenLabs TTS API.
+  </Card>
+  <Card title="Websockets" icon="regular comments" href="/api-reference/websockets">
+    Learn how to use our API with websockets.
+  </Card>
+  <Card
+    title="Join Our Discord"
+    icon="brands discord"
+    href="https://discord.gg/elevenlabs"
+  >
+    A great place to ask questions and get help from the community.
+  </Card>
+  <Card
+    title="Integration Guides"
+    icon="regular rectangle-pro"
+    href="/developer-guides/how-to-use-tts-with-streaming"
+  >
+    Learn how to integrate ElevenLabs into your workflow.
+  </Card>
+</CardGroup>

fern/api-reference/websockets.mdx

@@ -1,6 +1,6 @@
 ---
 title: Websockets
-slug: api-reference/websockets
+slug: api-reference/websockets/overview
 ---
 
 
@@ -162,15 +162,15 @@ The server will always respond with a message containing the following fields:
 }
 ```
 
-<ResponseField name="audio" type="string" optional="true">
+<ParamField path="audio" type="string" optional="true">
   A generated partial audio chunk, encoded using the selected output_format, by default this is MP3 encoded as a base64 string.
-</ResponseField>
+</ParamField>
 
-<ResponseField name="isFinal" type="boolean" optional="true">
+<ParamField path="isFinal" type="boolean" optional="true">
   Indicates if the generation is complete. If set to `True`, `audio` will be null.
-</ResponseField>
+</ParamField>
 
-<ResponseField name="normalizedAlignment" type="string" optional="true">
+<ParamField path="normalizedAlignment" type="string" optional="true">
   Alignment information for the generated audio given the input normalized text sequence.
   <Expandable title="properties">
 
@@ -186,9 +186,9 @@ The server will always respond with a message containing the following fields:
     The list of characters in the normalized text sequence that corresponds with the timings and durations. This list is used to map the characters to their respective starting times and durations.
   </ParamField>
   </Expandable>
-</ResponseField>
+</ParamField>
 
-<ResponseField name="alignment" type="string" optional="true">
+<ParamField path="alignment" type="string" optional="true">
   Alignment information for the generated audio given the original text sequence.
   <Expandable title="properties">
 
@@ -204,7 +204,7 @@ The server will always respond with a message containing the following fields:
     The list of characters in the original text sequence that corresponds with the timings and durations. This list is used to map the characters to their respective starting times and durations.
   </ParamField>
   </Expandable>
-</ResponseField>
+</ParamField>
 
 ## Path parameters