Text to speech API in Python

From $0.08 per successful call · failed calls are never charged · no account needed · Markdown version: /guides/text-to-speech-api-python.md

Turn text into speech from Python with one HTTP request: no TTS model to install, the answer is JSON with a URL to the generated audio file.

Text to speech API: monthly plans and one-off packs, one API key.

Python example

import os, requests

API = "https://glyphcall.com/text-to-speech"
HEADERS = {"Authorization": f"Bearer {os.environ['API_KEY']}"}

def speak(text, voice="luna"):
    r = requests.get(API, params={"text": text, "voice": voice}, headers=HEADERS)
    r.raise_for_status()
    return r.json()  # includes the URL of the audio file

Set API_KEY to a key from /credits.

When an agent wants this

Text to speech: long text, up to 2,000 characters as one MP3, natural voices $0.08

Text to speech for a paragraph or a page: up to 2,000 characters as one MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2, ; fr, zh, ja and ko are retired with MeloTTS (Workers AI, 20 Nov 2026). Pick a voice by name or leave the default. Use for narration, article and summary read-outs, voice replies, IVR prompts and accessibility; for a sentence of up to 300 characters ai_speech costs less.

Inputs: text (required): Text to speak, up to 2,000 characters; lang: Language: en or es (Aura-2 MP3, many voices); fr, zh, ja and ko are retired (MeloTTS was removed from Workers AI, 20 Nov 2026); default en; voice: 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: 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); sample_rate: Sample rate in Hz for wav and pcm (8000, 16000, 24000 default, 32000, 48000) or ulaw/alaw (8000 default, 16000); pronunciations: How to say words: JSON {"Nginx":"engine x","GIF":"jif"} or Nginx=engine x, GIF=jif (up to 50, whole words, any case).

Not in the free calls (it costs capacity per call); pay from the first call.

With a card key from /credits, in a header or, when your client can only fetch a URL, in the URL:

curl -H "Authorization: Bearer adt_…" "https://glyphcall.com/text-to-speech?text=Your%20order%20has%20shipped.%20It%20leaves%20our%20warehouse%20today%20and%20should%20reach%20you%20within%20three%20working%20days.%20You%20can%20follow%20the%20parcel%20with%20the%20link%20in%20your%20confirmation%20e-mail."
curl "https://glyphcall.com/text-to-speech?text=Your%20order%20has%20shipped.%20It%20leaves%20our%20warehouse%20today%20and%20should%20reach%20you%20within%20three%20working%20days.%20You%20can%20follow%20the%20parcel%20with%20the%20link%20in%20your%20confirmation%20e-mail.&api_key=adt_…"

Without a key the same URL answers 402 Payment Required with x402 and MPP terms, so a wallet client pays USDC per call and retries. Over MCP (https://glyphcall.com/mcp) this tool is text_to_speech.

Example result
{
  "contentType": "audio/mpeg",
  "audioBase64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjMuMTAwAAAA…",
  "bytes": 187392,
  "lang": "en",
  "voice": "luna",
  "characters": 168,
  "parts": 1,
  "model": "@cf/deepgram/aura-2-en"
}

Tool page, inputs and limits

Questions

Do I need a TTS library?

No. The speech is generated on the server; your script only needs an HTTP client such as requests.

What does it return?

JSON with the audio URL and format; fetch that URL to get the MP3.

How do I pay?

Each successful call costs the tool's price; failed calls are not charged. Then pay with card credits from $1 (the key goes in an Authorization header or as api_key= in the URL) or per call in USDC over x402 or MPP. No account is needed.