Text to speech API
Send text and get one audio file back: a natural voice as an MP3 in English or Spanish, French, Chinese, Japanese and Korean too, or a low-cost English voice. One GET request, JSON with a URL to the audio, no account and failed calls free.
Text to speech API: monthly plans and one-off packs, one API key.
When an agent wants this
- Add natural text to speech to an app without a model or a cloud vendor
- Read an article, notification or IVR prompt aloud
- Pick a shorter cheap voice or a longer natural voice by task
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"
}Text to speech (TTS): natural voices, audio file $0.01
Turn up to 300 characters of text into natural, human-sounding speech: MP3 in English (40 voices) or Spanish (10 voices) with Deepgram Aura-2, or WAV in French, Chinese, Japanese or Korean with MeloTTS (one voice each). Pick a voice by name or leave the default. Use for voice replies, audio notes, accessibility and phone or chat bots; for up to 2,000 characters use text_to_speech.
Inputs: text (required): Text to speak, up to 300 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/ai/speech?text=Your%20payment%20was%20received.%20Thank%20you!"
curl "https://glyphcall.com/ai/speech?text=Your%20payment%20was%20received.%20Thank%20you!&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 ai_speech.
Example result
{
"contentType": "audio/mpeg",
"audioBase64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjMuMTAwAAAA…",
"bytes": 41472,
"lang": "en",
"voice": "luna",
"characters": 37,
"model": "@cf/deepgram/aura-2-en"
}Cheap text to speech: up to 2,000 characters in English as one MP3 $0.04
Low-cost text to speech for longer English text: up to 2,000 characters as one MP3 (base64) with Deepgram Aura-1, 12 voices. Half the price per character of text_to_speech, with a slightly less natural voice. Pick a voice by name or leave the default. Use for narration drafts, read-aloud of articles and summaries, notifications and accessibility at volume; for the most natural voices or Spanish use text_to_speech.
Inputs: text (required): Text to speak, up to 2,000 characters; voice: Voice name: angus, asteria, arcas, orion, orpheus, athena, luna, zeus, perseus, helios, hera, stella. OpenAI voice names map to the nearest one. Default: luna.
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/lite?text=Your%20order%20has%20shipped%20and%20should%20reach%20you%20within%20three%20working%20days."
curl "https://glyphcall.com/text-to-speech/lite?text=Your%20order%20has%20shipped%20and%20should%20reach%20you%20within%20three%20working%20days.&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_lite.
Example result
{
"contentType": "audio/mpeg",
"audioBase64": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjMuMTAwAAAA…",
"bytes": 61440,
"voice": "luna",
"characters": 72,
"parts": 1,
"model": "@cf/deepgram/aura-1"
}Questions
How long can the text be?
Up to 300 characters with the short tool (ai/speech), 2,000 with text-to-speech, and a low-cost English voice with text-to-speech/lite.
Do I need an account?
No. Free calls to start, then a paid key or per-call USDC; failed calls are never charged.
Can I use my OpenAI or ElevenLabs code?
Yes. POST /v1/audio/speech (OpenAI shape) and /v1/text-to-speech/{voice_id} (ElevenLabs shape) work with a base-URL change.
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.