Text-to-Speech

Convert text to natural-sounding speech

Text-to-Speech

Generate audio from text with multiple voice options and formats.

Create Speech

POST /v1/audio/speech

Generate audio from input text.

Request Body

Parameter	Type	Required	Default	Description
model	string	Yes	—	TTS model: tts-1, tts-1-hd, kokoro-82m
input	string	Yes	—	Text to convert (max 4096 chars)
voice	string	Yes	—	Voice to use (see below)
response_format	string	No	mp3	Audio format
speed	number	No	1.0	Speed multiplier (0.25-4.0)

Available Voices

Voice	Description
alloy	Neutral, balanced
echo	Warm, conversational
fable	Expressive, storytelling
onyx	Deep, authoritative
nova	Friendly, upbeat
shimmer	Soft, gentle

Kokoro voices (for kokoro-82m model):

• af_bella, af_sarah — Female American
• am_adam, am_michael — Male American
• bf_emma, bf_isabella — Female British
• bm_george, bm_lewis — Male British

Audio Formats

Format	Description
mp3	Compressed, widely compatible
opus	Efficient, good for streaming
aac	Apple-friendly
flac	Lossless
wav	Uncompressed
pcm	Raw audio

Example Request

cURL

curl -X POST https://api.ymq-01.edge.polargrid.ai:55111/v1/audio/speech \
  -H "Authorization: Bearer pg_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello from PolarGrid!",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3

Response

Returns raw audio bytes in the requested format.

Streaming TTS

For real-time audio playback, use streaming:

JavaScript

for await (const chunk of client.textToSpeechStream({
  model: 'tts-1',
  input: 'Long text to convert to speech...',
  voice: 'nova',
})) {
  // Process audio chunks as they arrive
  audioStream.write(chunk);
}

Streaming TTS is available in mock mode. Production streaming coming soon.