> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.deepgram.com/changelog/2026/5/4/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server.

## Aura-2 Voice Controls — Speed and Pronunciation

Aura-2 TTS voices now support runtime speed and pronunciation controls in English and Spanish, available on both batch and streaming WebSocket endpoints. Together, these controls give developers finer-grained tools to improve naturalness — tuning pacing and correcting pronunciation to match their needs.

Speed control adjusts the speaking rate of generated audio while maintaining natural prosody, with a supported range of 0.7x–1.5x. For Spanish voices, the recommended range is 0.9x–1.5x; values below 0.9x may introduce disfluencies.

Pronunciation control overrides the default pronunciation of specific words using inline IPA notation, e.g. `The patient was prescribed \{"word": "dupilumab", "pronounce": "duːˈpɪljuːmæb"\}.`

See [Voice Controls](/docs/tts-voice-controls) for details.

### Voice Agent

These controls are also supported when using Aura-2 inside the Voice Agent API: set `speed` once at the session level, and have the LLM emit pronunciation overrides inline. See [Voice Agent TTS Controls](/docs/voice-agent-tts-controls) for the recommended setup.

### Self-Hosted

These controls are powered by an updated Aura-2 voice-pack model. Self-hosted deployments using a voice-pack from before [the April 2026 release](/changelog/2026/4/30) will return `400 Bad Request` on requests including `speed` or `pronounce` parameters. See the [April 2026 self-hosted release notes](/changelog/2026/4/30) for voice-pack version requirements and upgrade instructions.