xAI TTS v1
xAI TTS v1 · xAI — Text to audio · 71 voices · 5 file formats. Call it through one queue API and pay for the options you pick.
modellane/xai-tts-v1 · Text to audio · xAI
Text to audio model: 71 voices, 5 file formats.
- Vendor
- xAI
- Task
- Text to audio
- Output
- Audio
- Price
- Based on text length
Input parameters
- Text
text— required The text fed into the generation. - Language
language— required, options: Auto, English, Chinese (Mandarin), Arabic (Egypt), Arabic (Saudi Arabia), Arabic (UAE), Bengali, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese (Brazil), Portuguese (Portugal), Russian, Spanish (Mexico), Spanish (Spain), Turkish, Vietnamese - Voice ID
voice_id— optional, options: Ara, Eve, Leo, Rex, Sal, jpi39icg, d18jlf6v, 33g9t0jl, 26w6ihxi, dr8gqysu, wy0m9l5w, om17cury, x7avnu1k, bcs7l2c3, hqxr4yub, h27ltdnz, 89q2pnko, 73xd5dum, 0p0rt7o1, Hbxkrnwm, 69smp8rm, yis75yfp, ekhwx401, jupvcf34, 0hhfxxqq, 0ih5oi34, gwnexu6y, 97zmdc6s, fc7de6afcf6c, 7a9ee820b342, 0895a5b8ce5c, f8cf5c2c78d4, 96819d0bd28d, 79f3a8b96d43, 78a495fdbb39, e22152e06fd8, 490ea3be50b1, 1f046a033914, dfe7b9e7d217, c3a2c594479e, 83c6f4fea98e, 34fd4dce1ba3, d634b6da3d3b, 670a0c3ac005, 182a91893636, d0cb9ff07d95, b1a7441b97a1, bf9fe5b5f981, b5ae17439907, a0401c9101f8, 23be42535a45, abfbdf26f115, 6da5baee46d0, 3d030bc92a87, a13662ba951c, 58d27475085e, 247783ebdd51, 244e27b39200, 97fabd54445f, 37329fd8895a, 2badb5f46b1e, 1b12d5daee6b, 908c4626660f, 4ff93971bfdc, 70013edeb8e8, 35c8d7f60dc8, 23468361b4ef, 458705c07139, 41321eb41295, 40f31906b23d, 3a7889066fa2 - Audio codec
codec— optional, options: MP3, WAV, PCM, Mulaw, Alaw - Sample rate
sample_rate— optional, default: 24000, options: 8000, 16000, 22050, 24000, 44100, 48000 The sample rate of the audio output; a higher value makes the file larger. - Bit rate
bit_rate— optional, default: 128000, options: 32000, 64000, 96000, 128000, 192000 - Speed
speed— optional, default: 1, range: 0.7–1.5 - Text normalization
text_normalization— optional, default: No - Streaming latency optimization
optimize_streaming_latency— optional, default: Best quality (no optimization), options: Best quality (no optimization), Lower latency, minor quality tradeoff, Lowest latency, noticeable quality tradeoff
Output and retention
The generated file and your input are kept for seven days and then deleted.
Queue API
Submit to the queue: POST /v1/queue/modellane/xai-tts-v1
Status, result, cancellation and error codes work the same for every model; see the API docs.
Playground
Everything on this page is public; you need an account to run the model.