L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

xai-grok-tts-text-to-speech

xai-grok-tts-text-to-speech

xAI | Grok TTS | Text to Speech. Convert text to speech with multiple voice options and audio format controls. Triggers: tts, text to speech, grok, xai, voice, audio

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: xai-grok-tts-text-to-speech description: "xAI | Grok TTS | Text to Speech. Convert text to speech with multiple voice options and audio format controls. Triggers: tts, text to speech, grok, xai, voice, audio" allowed-tools: Bash(curl *), WebFetch

xAI | Grok TTS | Text to Speech

Convert text to speech using xAI's Grok TTS engine with 5 voice options, multiple audio codecs, and configurable sample rates. Supports 20+ languages with automatic detection.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "xai-grok-tts-text-to-speech",
    "version": "0.0.1",
    "input": {
      "text": "Hello! Welcome to our product demonstration. Let me walk you through the key features.",
      "voice_id": "eve",
      "output_format": "mp3",
      "sample_rate": 24000
    }
  }'

Parameters

ParameterTypeDefaultDescription
bit_rateinteger128000MP3 bit rate in bps (MP3 codec only). 32000: low/small file. 128000: standard.
output_formatstringmp3Audio codec. mp3: general use. wav: lossless. enum: mp3, wav, pcm, mulaw, alaw
sample_rateinteger24000Audio sample rate in Hz. 8000: narrowband. 16000: wideband. 22050/24000: standard.
textstringText to convert to speech. Maximum 15000 characters. Supports 20+ languages.
voice_idstringeveVoice selection. eve: energetic/upbeat. ara, rex, sal, leo also available. enum: eve, ara, rex, sal, leo

Examples

Standard MP3 with Eve voice:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "xai-grok-tts-text-to-speech",
    "version": "0.0.1",
    "input": {
      "text": "The future of artificial intelligence is both exciting and full of possibilities.",
      "voice_id": "eve",
      "output_format": "mp3"
    }
  }'

High-quality WAV with Rex voice:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "xai-grok-tts-text-to-speech",
    "version": "0.0.1",
    "input": {
      "text": "Breaking news: Scientists have made a groundbreaking discovery in renewable energy technology.",
      "voice_id": "rex",
      "output_format": "wav",
      "sample_rate": 24000
    }
  }'

Low bit-rate MP3 for telephony:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "xai-grok-tts-text-to-speech",
    "version": "0.0.1",
    "input": {
      "text": "Your appointment is confirmed for tomorrow at 3 PM. Press 1 to confirm or 2 to reschedule.",
      "voice_id": "sal",
      "output_format": "mulaw",
      "sample_rate": 8000
    }
  }'

Related Models

Documentation

Skills enregistrées