> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

### Agents Platform

- **Azure OpenAI custom LLM support**: Added support for Azure-hosted OpenAI models in custom LLM configurations. When using an Azure endpoint, a new required field for [API version](/docs/api-reference/agents/create#request.body.conversation_config.agent.prompt.custom_llm.api_version) is now available in the UI.
- **Genesys output variables**: Added support for output variables when using [Genesys integrations](/docs/eleven-agents/phone-numbers/c-caa-s-integrations/genesys), enabling better call analytics and data collection.
- **Gemini 2.5 Preview Models Deprecation**: [Models](/docs/api-reference/agents/create#request.body.conversation_config.agent.prompt.llm) `gemini-2.5-flash-preview-05-20` and `gemini-2.5-flash-preview-04-17` have been deprecated in Agents Platform as they are being deprecated on 15th July by Google. All agents using these models will automatically be transferred to `gemini-2.5-flash` the next time they are used. No action is required.
- **WebRTC rollout**: Began progressive rollout of WebRTC capabilities for improved connection stability and performance. WebRTC mode can be selected in the React SDK and is used in 11.ai.
- **Keypad touch tone**: Fixed an issue affecting playing keypad touch tones on Twilio. See [keypad touch tone documentation](/docs/eleven-agents/customization/tools/system-tools/play-keypad-touch-tone).

### Voices

- **Language collection navigation**: Added quick navigation from language preview collections to view all available voices in that language, making it easier to explore voice options by language.

### Text to Voice

- **Preview streaming**: Added new streaming endpoint for Text to Voice previews, allowing real-time streaming of generated voice previews via `/v1/text-to-voice/{generated_voice_id}/stream`.
- **Enhanced voice design**: Added [`stream_previews`](/docs/api-reference/text-to-voice/design#request.body.stream_previews) option to voice design endpoint, enabling streaming-only preview generation for improved performance.
- **Improved parameter controls**: Enhanced [`loudness`](/docs/api-reference/text-to-voice/design#request.body.loudness), quality, and guidance scale parameters with better control options for more precise voice generation.

### ElevenCreative Studio

- **Podcast customization**: Added support for [intro](/docs/api-reference/studio/create-podcast#request.body.intro) and [outro](/docs/api-reference/studio/create-podcast#request.body.outro) text in podcast creation, along with custom instructions prompts for better style and tone control.

### SDKs

- **[JavaScript SDK v2.6.0](https://github.com/elevenlabs/elevenlabs-js)**: Released with latest API support and improvements
- **[Python SDK v2.7.1](https://github.com/elevenlabs/elevenlabs-python)**: Released with bug fixes and enhancements
- **[@elevenlabs/client v0.3.0](https://github.com/elevenlabs/packages/tree/main/packages/client)**: Updated client library with support for User IDs in Agents Platform.
- **[@elevenlabs/react v0.3.0](https://github.com/elevenlabs/packages/tree/main/packages/react)**: Add WebRTC debug support.

### API

<Accordion title="View API changes">

## New Endpoints

- Added 1 new endpoint:
  - [Stream Text to Voice Preview](/docs/api-reference/text-to-voice/stream) - Stream generated voice previews in real-time

## Updated Endpoints

### Text to Voice

- [Create voice previews](/docs/api-reference/text-to-voice/create) - Enhanced `loudness`, `quality`, and `guidance_scale` parameter descriptions
- [Design voice](/docs/api-reference/text-to-voice/design) - Added `stream_previews` property for streaming-only preview generation

### ElevenCreative Studio

- [Create podcast](/docs/api-reference/studio/create-podcast) - Added `intro`, `outro`, and `instructions_prompt` properties

### Agents Platform

- [Simulate conversation](/docs/api-reference/agents/simulate-conversation) - Enhanced simulation configuration with improved parameter descriptions
- [Stream simulate conversation](/docs/api-reference/agents/simulate-conversation-stream) - Enhanced simulation configuration with improved parameter descriptions
- [Get Agents Platform settings](/docs/api-reference/workspace/get) - Updated RAG retention period configuration
- [Update Agents Platform settings](/docs/api-reference/workspace/update) - Updated RAG retention period configuration
- [Retry batch calling](/docs/api-reference/batch-calling/retry) - Added batch retry functionality

</Accordion>

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.