Text to speech

POST /v1/audio/speech takes text and returns audio bytes. Three models serve it:

Model	Billing	Formats	Voices
`xai/grok-voice-tts-1.0`	$15.00 / 1M characters	mp3, wav, pcm	26 voices, including eve, carina and zagan
`google/gemini-3.8-flash-tts`	$1.00 / 1M input tokens, $18.00 / 1M output tokens ($0.50 / $9.00 through December 31, 2026)	wav, pcm	30 voices, including Kore, Puck and Zephyr
`google/gemini-3.1-flash-tts-preview`	$1.00 / 1M input tokens, $20.00 / 1M output tokens	wav, pcm	30 voices, including Kore, Puck and Zephyr

Generate speech

curl https://api.impossibl.com/v1/audio/speech \
  -H "Authorization: Bearer $IMPOSSIBL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xai/grok-voice-tts-1.0",
    "input": "hello there, this is a test",
    "voice": "eve"
  }' \
  --output speech.mp3

The response body is the audio itself, so write it to a file. Failed upstream requests are not charged.

Voices

Voices are the provider’s own ids, not OpenAI aliases: eve for Grok, Kore for Gemini. Ids match case-insensitively, so EVE and kore work too. An unknown voice returns a 400 listing the ones that model has. GET /v1/models carries the full list per model, so nothing needs to be hardcoded.

curl https://api.impossibl.com/v1/models \
  -H "Authorization: Bearer $IMPOSSIBL_API_KEY" | jq '.data[] | select(.endpoints == ["/v1/audio/speech"]) | {id, voices}'

Audio formats

Each model defaults to its native format: mp3 for Grok, wav for Gemini. Gemini generates 24 kHz mono PCM and nothing else, so it serves wav and pcm only. Asking a model for a format it cannot produce returns a 400 rather than quietly substituting another one.

curl https://api.impossibl.com/v1/audio/speech \
  -H "Authorization: Bearer $IMPOSSIBL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash-tts",
    "input": "hello there, this is a test",
    "voice": "Kore",
    "response_format": "wav"
  }' \
  --output speech.wav

Limits and billing units

Grok Voice bills per character of input, capped at 15,000 characters per request, and speed accepts 0.7 to 1.5. Both Gemini Flash TTS models bill tokens the way every other Gemini model does and accept up to 8,192 input tokens. They have no rate control, so a speed other than 1 returns a 400 instead of quietly giving you normal-speed audio. All three models accept inline expressive tags in input to steer delivery.

Get started

Build

Modalities

Manage

Generate speech

Voices

Audio formats

Limits and billing units

​Generate speech

​Voices

​Audio formats

​Limits and billing units

Generate speech

Voices

Audio formats

Limits and billing units