菜单
Streaming text-to-speech via ElevenLabs WebSocket API with real-time audio generation
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Edit, transform, and enhance images using AI models
Extract text from images using OCR and vision AI
Neural text-to-speech via Amazon Polly
Speaker diarization — identifies and tracks who is speaking at each moment in an audio stream
Semantic endpoint detection — uses an LLM to classify whether the user's utterance is a complete thought, reducing false turn boundaries on mid-sentence pauses
Batch speech-to-text via Google Cloud Speech-to-Text API
| name | streaming-tts-elevenlabs |
| description | Streaming text-to-speech via ElevenLabs WebSocket API with real-time audio generation |
| category | voice |
Low-latency streaming text-to-speech using the ElevenLabs WebSocket Streaming API. Maintains a persistent WebSocket connection per session and streams audio chunks as MP3 data as soon as each sentence boundary is reached, enabling near-instant audio playback.
Set ELEVENLABS_API_KEY in your environment or agent secrets store.
., ?, !) for low-latency outputIn agent.config.json:
{
"voice": {
"tts": "elevenlabs"
}
}
Provider-specific options via providerOptions:
{
"voice": {
"tts": "elevenlabs",
"providerOptions": {
"voiceId": "21m00Tcm4TlvDq8ikWAM",
"modelId": "eleven_turbo_v2",
"stability": 0.5,
"similarityBoost": 0.75,
"style": 0.0,
"useSpeakerBoost": true
}
}
}
| Event | Payload | Description |
|---|---|---|
audio_chunk | EncodedAudioChunk | MP3 audio buffer ready for playback |
utterance_complete | { text, durationMs } | ElevenLabs signalled final audio generation done |
cancelled | { remaining: string } | Session was cancelled; remaining text not rendered |
error | Error | WebSocket or synthesis error |
close | — | Session fully terminated |