API docs / Audio models
speech-2.8-hd API
Convert text to natural-sounding speech with studio-grade quality audio. Supports 32 languages including English, Chinese, Spanish, French, German, Japanese, Korean, Arabic, Russian, and Portuguese. Features 17+ preset voices spanning different genders, ages, and speaking styles including Deep_Voice_Man, Imposing_Manner, Lively_Girl, Casual_Guy, Young_Knight, and Abbess. Provides expressive emotion control with options for happy, calm, sad, angry, fearful, disgusted, surprised, neutral, and fluent delivery styles. Supports voice cloning capabilities requiring only 5 seconds of reference audio. Includes natural interjections like (laughs), (sighs), (coughs), (gasps), (humming), (whistles), (sneezes), and (applause). Allows fine-grained control over speech speed (0.5x-2x), pitch (-12 to +12 semitones), volume (0-10), and custom pause insertion using <#x#> markers. Outputs audio in MP3, WAV, FLAC, and PCM formats with configurable sample rates (8,000-44,100 Hz) and bitrates (32,000-256,000 bps). Processes text inputs up to 10,000 characters with optional subtitle metadata including sentence timestamps.
- Model id
minimax/speech-2.8-hd- Provider
- minimax
- Output
- Audio
- Price
- From 1 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "minimax/speech-2.8-hd". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "minimax/speech-2.8-hd",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light"
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
promptrequired | string | Text to narrate (max 10,000 characters). Use markers like <#0.5#> to insert pauses in seconds. Up to 10000 characters |
voice | string | Voice to synthesize. Pick any MiniMax system voice (e.g. See the full list of voices in the README. Default: |
output_format | string | Default: One of: mp3, wav, flac, pcm |
bitrate | number | Default: One of: 32000, 64000, 128000, 256000 |
channel | string | Default: One of: mono, stereo |
emotion | string | Default: One of: auto, happy, sad, angry, fearful, disgusted, surprised, calm, fluent, neutral |
english_normalization | boolean | Improve number/date reading for English text (adds a small amount of latency). Default: |
language_boost | string | Default: One of: None, Automatic, Chinese, Chinese,Yue, Cantonese, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans |
pitch | number | Semitone offset applied to the voice (−12 to +12). Default: Min -12 · Max 12 |
sample_rate | number | Default: One of: 8000, 16000, 22050, 24000, 32000, 44100 |
speed | number | Speech speed multiplier (0.5–2.0). Lower is slower, higher is faster. Default: Min 0.5 · Max 2 |
subtitle_enable | boolean | Return MiniMax subtitle metadata with sentence timestamps (non-streaming only). Default: |
volume | number | Relative loudness. 1.0 is default MiniMax gain. Range 0–10. Default: Min 0 · Max 10 |