ComfyUI Node
Grok TTS · Text to Speech
71 voices across 20 languages with speech tags 2.7 credits ($0.027) per 1k characters. Model: xai/grok-tts/text-to-speech Fields, prices and examples: https://popnow.ai/docs/models/grok-tts
Grok TTS · Text to Speech
- audio
- task id
◄text►
◄voice_idEve · female · multilingual (default)►
◄languageAuto-detect►
◄speed1.00►
◄output_formatMP3►
◄sample_rate24 kHz►
◄bitrate128 kbps►
◄text_normalizationfalse►
◄optimize_streaming_latency0 — best quality►
CategoryPopNow/Audio/xAI
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | The words to be spoken, with optional speech tags such as [laugh] or <whisper>…</whisper>. Billed per 1,000 characters, tags included. | |
| voice_id | COMBO | Eve · female · multilingual (default) | Preset voice. Eve, Ara, Leo, Rex and Sal speak every supported language; the others are tuned for one language. |
| language | COMBO | Auto-detect | Reading language, or auto to detect it from the text. |
| speed | FLOAT | 1.000.7–1.5 | Speaking speed from 0.7 (slower) to 1.5 (faster). |
| output_format | COMBO | MP3 | Audio encoding. pcm, mulaw and alaw are raw streams without a file header, for phone systems. |
| sample_rate | COMBO | 24 kHz | Sample rate in Hz. 8000 for phone lines, 44100 or 48000 for studio work. |
| bitrate | COMBO | 128 kbps | MP3 bit rate in bits per second. Only applies to mp3. |
| text_normalization | BOOLEAN | false | Rewrite numbers, abbreviations and symbols as spoken words before reading. |
| optimize_streaming_latency | COMBO | 0 — best quality | Streaming latency level: 0 best quality, 1 smaller first chunk, 2 smallest first chunk with more quality trade-off at chunk boundaries. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | Several results come back as a batch; Save Audio writes one file each. |
| task id | STRING | The PopNow task id, for the API console logs or support. |