Text to speech API, TTS: natural voices, MP3 audio from text
Text to speech API: turn up to 300 characters of text into natural, human-sounding speech as an MP3 (base64) with Deepgram Aura-2 voices in English (40) or Spanish (10), or as a WAV in French, Chinese, Japanese or Korean (MeloTTS). Pick a voice by name or keep the default. Use for voice replies, narration, audio notes, IVR prompts and accessibility.
Inputs
| Name | Type | Description |
|---|---|---|
text (required) | string | Text to speak, up to 300 characters |
lang | string | Language: en or es (Aura-2 MP3, many voices), fr, zh, ja or ko (MeloTTS WAV, one voice each); default en. One of: en, es, fr, zh, ja, ko. |
voice | string | Voice name. English: amalthea, andromeda, apollo, arcas, aries, asteria, athena, atlas, aurora, callista, cora, cordelia, delia, draco, electra, harmonia, helena, hera, hermes, hyperion, iris, janus, juno, jupiter, luna, mars, minerva, neptune, odysseus, ophelia, orion, orpheus, pandora, phoebe, pluto, saturn, thalia, theia, vesta, zeus. Spanish: sirio, nestor, carina, celeste, alvaro, diana, aquila, selena, estrella, javier. Default: luna (en), aquila (es) |
format | string | Audio format: mp3 (default), wav, pcm (raw 16-bit little-endian mono), ulaw or alaw (8 kHz telephony, e.g. Twilio), opus (Ogg) or flac. opus and flac only for text spoken in one part (up to 450 characters). One of: mp3, wav, pcm, ulaw, alaw, opus, flac. |
sample_rate | string | Sample rate in Hz for wav and pcm (8000, 16000, 24000 default, 32000, 48000) or ulaw/alaw (8000 default, 16000) |
pronunciations | string | How to say words: JSON {"Nginx":"engine x","GIF":"jif"} or Nginx=engine x, GIF=jif (up to 50, whole words, any case) |
Request
Over HTTP, with a card key from /credits:
curl -H "Authorization: Bearer adt_…" "https://lex.glyphcall.com/ai/tts?text=Your%20payment%20was%20received.%20Thank%20you!"
Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
Example result
{
"contentType": "audio/mpeg",
"audioBase64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjMuMTAwAAAA…",
"bytes": 41472,
"lang": "en",
"voice": "luna",
"characters": 37,
"model": "@cf/deepgram/aura-2-en"
}
From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is ai_tts, and the first 25 successful calls are free:
https://lex.glyphcall.com/mcp