ChindaTTS Text-to-Speech

Speaks Thai, or Thai mixed with English, in one of three voices and eight speaking styles, or in a voice cloned from a short clip, and returns a WAV or MP3 file at 48 kHz.

Alpha

The service is in alpha and may be intermittently unavailable.

POST/v3/store/audio/tts

+1 endpoints

Try it

• Price1 ICper 400 characters
• Served2.1Mcalls

• v3.0
• Active

Input

text

สวัสดีค่ะ ยินดีต้อนรับค่ะ

voice

kaimook

style

friendly

format

mp3

OutputPOST /v3/store/audio/tts

HTTP/1.1 200 OK
Content-Type: audio/mpeg
X-Sample-Rate: 48000

<MP3 audio, mono, 48 kHz>

Every field, under ResponseOther endpoints: /clone see Request

Request

curl -X POST https://api.iapp.co.th/v3/store/audio/tts \
  -H "apikey: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "สวัสดีค่ะ ยินดีต้อนรับค่ะ", "voice": "kaimook", "style": "friendly", "format": "mp3"}' \
  --output speech.mp3

Response

200OK. The fields are explained under Response.

HTTP/1.1 200 OK
Content-Type: audio/mpeg
X-Sample-Rate: 48000

<MP3 audio, mono, 48 kHz>

Request

JSON to speak in a voice, multipart/form-data to clone one. Each costs 1 IC per 400 characters of text.

Endpoint	Returns
POST /v3/store/audio/tts	A WAV or MP3 file, 48 kHz, in the voice and style asked for
POST /v3/store/audio/tts/clone	A WAV or MP3 file, 48 kHz, in the voice of an uploaded clip

The older paths /v3/store/audio/tts/tts and /v3/store/audio/tts/tts/clone reach the same two endpoints.

Headers

apikeystringrequired

Your API key, created under API Keys in the control panel.

Body

textstringrequired

The text to speak, up to 1,200 characters (1,000 on /clone), about 100 seconds of audio. Send longer text in parts, split at the end of a sentence.

voicestringdefault:kaitom

kaitom, kaimook or kaidang; see Voices and styles. Not on /clone, which speaks in the uploaded voice.

stylestringdefault:neutral

neutral, friendly, cheerful, calm, serious, sad, excited or empathetic. A style changes the tone, not the voice; any other value is refused with 400.

formatstringdefault:wav

wav or mp3.

filefile

/clone only, required there: 10 to 20 seconds of clean speech by one speaker, WAV or MP3, up to 20 MB. A shorter or noisy clip is refused with 400.

consentboolean

/clone only, required there: true to confirm the voice is yours or its speaker has agreed. Without it the request is refused with 400.

denoisebooleandefault:false

/clone only: removes background noise from the clip before it is used.

Response

Headers

Content-Typestring

audio/wav, or audio/mpeg when format is mp3.

X-Sample-Ratestring

48000.

Body

audiobinary

The audio, ready to play or save: a WAV file (16-bit, mono, 48 kHz) or an MP3. Cloning answers the same way.

Status codes

Code	Meaning
400	Malformed JSON, text with nothing to speak, or an unknown style; on /clone, no consent, or a clip too short or too noisy
413	Text over 1,200 characters, or a clip over 20 MB
429	More requests than the key allows; wait, then retry
503	Busy; retry shortly

Details

Voices and styles

Voice	voice	Suits
Kaitom, the default	kaitom	A man's voice, for any use
Kaimook	kaimook	A woman's voice, bright and friendly: service, welcomes
Kaidang	kaidang	A man's voice: announcements, voice assistants

style	Sounds	For
neutral, the default	Plain, balanced	Information
friendly	Warm, easy	Chat, support, welcomes
cheerful	Bright, upbeat	Promotions, good news
calm	Slow, soft, soothing	Guidance, reassurance
serious	Firm, measured	Alerts, announcements, terms
sad	Slow, soft, low	Condolences, apologies
excited	Fast, energetic	Celebrations
empathetic	Gentle, caring	Sensitive support

Every voice speaks every style; all 24 pairs can be heard on the ChindaTTS page. The text is read as written, so write ค่ะ and คะ for Kaimook where Kaitom and Kaidang say ครับ.

Measured

Character error rate when the audio is transcribed back; lower is better.

Text	Character error rate
Everyday Thai	3.2%
Numbers, dates, currency	1.4%
Thai and English mixed	7.6%
Expressive styles	3.9%

A request of 100 characters takes about 1.5 seconds and one of 1,000 about 14.

Limits

• Thai and English; other scripts, emoji and symbols are dropped, not read aloud. Cloning is Thai only.
• 1,200 characters per request (1,000 on /clone), about 100 seconds of audio.
• 100 requests per second per API key.
• Punctuation sets the pauses. To fix how a brand or acronym is said, write it in Thai script: ไอแอป, not iApp.

Data handling

Text and reference clips are processed in memory and not kept after the response. Consent and notice under PDPA and GDPR remain with you as the data controller.

Deprecated endpoints

The V1 and V2 endpoints still answer, at the same price, but are no longer maintained. Move to /v3/store/audio/tts.

Endpoint	Was
/v3/store/speech/text-to-speech/kaitom, also /thai-tts-kaitom2/tts	V2, Kaitom voice
/v3/store/speech/text-to-speech/kaitom/v1, also /thai-tts-kaitom/tts	V1, Kaitom voice
/v3/store/speech/text-to-speech/cee, also /thai-tts-cee/tts	V1, Cee voice

To move, send JSON with text, and voice, style and format as needed, in place of form fields or a query string, and drop language: the language is detected. The answer is an audio file, ready to play. There is no Cee voice.

Changelog

Version	Changes
ChindaTTS, Oct 2026	Three voices (voice: kaitom, kaimook, kaidang), eight speaking styles (style) and a choice of WAV or MP3 (format). The answer is now an audio file, WAV at 48 kHz or MP3, in place of raw 24 kHz PCM: play or save it as it is, without adding a WAV header. Cloning takes style, format and denoise.
ChindaTTS	The V3 endpoints run on ChindaTTS, with the same request and response, up to 1,200 characters per request. The V1 and V2 endpoints are deprecated; see Deprecated endpoints.
V3	/v3/store/audio/tts replaces /v3/store/speech/text-to-speech/kaitom, with a JSON body, the language detected instead of a language mode, up to 10,000 characters, 24 kHz output, text normalisation for numbers, dates, currency, times and percentages, and voice cloning.