MiniMax Speech 2.8 HD
Text to speech
Starting price $0.17 / run
By MiniMax
MiniMax Speech-02 Turbo reads up to 5000 characters in a preset voice, with a chosen emotion and control over speed, pitch and volume.
minimax/speech-02-turboQuote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax/speech-02-turbo",
"input": {
"text": "Good morning! Today brings sunny spells, a light breeze and highs of around twenty degrees."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "minimax/speech-02-turbo", "quote_id": "QUOTE_ID", "input": {"text":"Good morning! Today brings sunny spells, a light breeze and highs of around twenty degrees."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
textrequired | string | Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character) |
voice_setting | object | Voice configuration settings |
audio_setting | object | Audio configuration settings |
language_boost | string (enum) | Enhance recognition of specified languages and dialects |
output_format | string (enum) | Format of the output content (non-streaming only) |
pronunciation_dict | object | Custom pronunciation dictionary for text replacement |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "audio", "url": "https://…", "mime_type": "audio/mpeg", "thumbnail_url": null }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
MiniMax Speech-02 Turbo turns text into speech. Pick a preset voice and an emotion such as happy, angry or surprised, then set speed, pitch and volume. Choose MP3, PCM or FLAC, mono or stereo, and the sample rate.
Language boost helps with a given language, Turkish among the options, and a pronunciation dictionary sets how names and terms are read.
Listen for names, pronunciation, pauses, clipping and the intended tone before publishing.