xAI 推出 Custom Voices，可在 Grok TTS 和 Voice Agent API 中使用克隆语音
Custom Voices Your voice. Your brand. Clone a voice from a short recording and use it across Grok Text to Speech and Speech to Speech APIs. Apr 30, 2026
xAI 推出 Custom Voices，录制约一分钟自然语音即可在不到两分钟内克隆出可投入生产的语音模型，适用于 Grok Text to Speech 和 Voice Agent API。
原文给出克隆流程、验证机制和定价细节，读者可判断这项语音克隆能力是否适合接入自己的应用。
Your voice. Your brand. Clone a voice from a short recording and use it across Grok Text to Speech and Voice Agent APIs.
Custom Voices Use Cases Custom Voices Voice Safety
Today, we're introducing Custom Voices. Clone your voice from a few seconds of audio and use it instantly across Grok Text to Speech and Voice Agent APIs.
Tyler
SpaceX Broadcast Host
ORIGINAL
CLONED
Use Cases
Custom Voices unlock a new class of applications.
Live Support
I need help with my recent order.
Of course! Let me pull up your order details.
Brand Voice Agents
Give your customer support agent a consistent, recognizable voice that matches your brand identity, not a generic preset.
Rec
In today's episode we dive deep into the future of AI and what it means for creators everywhere
Content Creators
Narrate videos, podcasts, and social posts in your own voice at scale, without re-recording every time.
Original
Preserved
Accessibility
Create personalized voices for individuals who have lost the ability to speak, preserving their vocal identity.
🇺🇸English
🇪🇸Spanish
🇫🇷French
🇩🇪German
🇨🇳Chinese
🇯🇵Japanese
Multilingual Teams
Deliver your CEO's keynote in every major language — naturally in English, Spanish, French, German, Chinese, Japanese, and more.
Narrator The ancient door creaked open...
Kira We need to move. Now.
Thane I have a bad feeling about this.
Gaming & Entertainment
Bring characters to life with unique voices without scheduling studio time for every line of dialogue.
Chapter 3
The Discovery
She opened the notebook and found the handwriting unmistakably her own though she had no memory of writing it
Podcasts & Audiobook Narration
Make your narrative engaging. Turn scripts into full audiobooks narrated in your own voice, chapter by chapter, without stepping into a studio.
Live Support
I need help with my recent order.
Of course! Let me pull up your order details.
Rec
In today's episode we dive deep into the future of AI and what it means for creators everywhere
Original
Preserved
🇺🇸English
🇪🇸Spanish
🇫🇷French
🇩🇪German
🇨🇳Chinese
🇯🇵Japanese
Narrator The ancient door creaked open...
Kira We need to move. Now.
Thane I have a bad feeling about this.
Chapter 3
The Discovery
She opened the notebook and found the handwriting unmistakably her own though she had no memory of writing it
Brand Voice Agents
Give your customer support agent a consistent, recognizable voice that matches your brand identity, not a generic preset.
Custom Voices
Clone your voice in under two minutes. Use it everywhere.
Record about a minute of natural speech in the xAI console. Our pipeline verifies you're the voice owner, processes your recording, and delivers a production-ready voice model, all in under two minutes. Your custom voice inherits every TTS capability: speech tags, multilingual output, and both REST and WebSocket streaming.
PASSPHRASE CHECK
RECORDING
My voice is my key
Step 1 Read a passphrase aloud to confirm your identity
Custom voices work everywhere our built-in voices do. Pass the voice_id to any TTS endpoint or use it with the Voice Agent API for real-time conversational agents.
There is no extra charge to use Text to Speech or Voice Agent APIs with custom voices.
Every custom voice goes through a two-stage verification process before it can be created. First, the speaker reads a verification phrase that our STT engine transcribes and matches in real time, confirming intent and presence. Then we compute speaker embeddings from the verification clip and the full recording to confirm they belong to the same person.
You can't clone a voice from a pre-existing recording, and you can't clone someone else's voice.
PASSPHRASE CHECK
RECORDING
My voice is my key
Passphrase Check
Read a verification phrase aloud. Our STT engine transcribes and matches it in real time, verifying your consent and presence.
SPEAKER SIMILARITY
IDLE
PASSPHRASE
RECORDING
Speaker Similarity
Speaker embeddings from the passphrase and the full recording are compared to confirm they belong to the same person.
来源：xAI：News · x.ai