Grok TTS speech tags, tested: what <loud>, <singing> and [laugh] actually do

A developer measured how xAI's Grok text-to-speech API speech tags affect output, finding that the <loud> tag raises median pitch from 195 Hz to 253 Hz while leaving loudness essentially unchanged (-20.7 to -20.9 dBFS RMS), making it more of an urgent delivery cue than a volume control. The <singing> tag stretched a 6.5-second clip to 8.4 seconds and pushed pitch from 189 Hz to 250 Hz. The developer also built a free, unaffiliated front-end for auditioning the tags across Grok's 28 voices, priced at $15 per million characters.

xAI's Grok text to speech API POST https://api.x.ai/v1/tts has 28 built-in voices, 20 languages and a set of speech tags you put straight into the text. The docs list the tags; they don't say how much each one changes. I measured a couple. js const res = await fetch 'https://api.x.ai/v1/tts', { method: 'POST', headers: { Authorization: Bearer ${process.env.XAI API KEY} , 'Content-Type': 'application/json', }, body: JSON.stringify { text: 'Stand back. <loud This is not a drill.</loud ', voice id: 'eve', language: 'en', output format: { codec: 'mp3', sample rate: 24000, bit rate: 128000 }, } , } ; const mp3 = Buffer.from await res.arrayBuffer ; language also takes auto . Price is $15 per million characters xAI pricing page, checked 2026-10-30 . pause , long-pause , hum-tune , laugh , chuckle , giggle , cry , tsk , tongue-click , lip-smack , breath , inhale , exhale , sigh . <soft , <whisper , <loud , <build-intensity , <decrease-intensity , <higher-pitch , <lower-pitch , <slow , <fast , <sing-song , <singing , <emphasis . Same sentence, voice Eve, English, one clip with and one without the tag. One clip each, so this is a quick check rather than a benchmark. | Tag | Length | Loudness RMS | Median pitch | |---|---|---|---| | none → <loud | 5.5 s → 5.5 s | -20.7 → -20.9 dBFS | 195 → 253 Hz | | none → <singing | 6.5 s → 8.4 s | — | 189 → 250 Hz | So <loud is closer to "raised, urgent delivery" than a volume control: if you need a louder file, normalise it afterwards. <singing stretches the words into a melody, which also makes the clip longer and, on a per-character price, not more expensive . If you want to hear the tags on all 28 voices before wiring up the API, I built a free front-end: Grok Text to Speech https://groktexttospeech.com/ . The speech tag reference https://groktexttospeech.com/grok-tts-speech-tags/ has a before/after sample for each group, and there are preset pages for whisper https://groktexttospeech.com/whisper-text-to-speech/ , shouting https://groktexttospeech.com/shouting-text-to-speech/ and singing https://groktexttospeech.com/singing-text-to-speech/ . It's an independent project, not affiliated with xAI.