API Many새 모델: Qwen 3.8 Max, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5

MiniMax · Audio · Text to Audio

Speech 2.6 Turbo API

Call Speech 2.6 Turbo with the same key and request shape as every other model in the catalog — from $0.081 per job.

Speech 2.6 Turbo example

WHY IT FITS

Inside the gateway

Minimax Speech 2.6 Turbo is a Text-to-Speech model offering ultra-human voice cloning, industry-leading text normalization, sub-250ms latency and 40+ language support. Route it through one API Many key: post the model id and your parameters, poll the returned job, and download the finished asset. Inputs are checked before dispatch and the quote is reserved up front from $0.081.

One credential

Speech 2.6 Turbo shares the same key, wallet and limits as the rest of the catalog.

Uniform contract

The request body, polling loop and result download are identical for every model.

Checked inputs

Declared fields are type- and range-checked before the job leaves the gateway.

text to audio

Text to Audio is exposed for Speech 2.6 Turbo without a bespoke client.

speech 2.6 turbo

Speech 2.6 Turbo is exposed for Speech 2.6 Turbo without a bespoke client.

audio

Audio is exposed for Speech 2.6 Turbo without a bespoke client.

OUTPUT

Sample outputs

INTEGRATION

Wire it in four steps

  1. Create a key

    Open the dashboard, mint a server-side API key and top up a small balance.

  2. Discover

    Call GET /v1/models to confirm minimax/speech-2.6-turbo, its live specification and the exact per-job rate.

  3. Submit

    POST /v1/jobs with the model id, your parameters and a fresh Idempotency-Key.

  4. Collect

    Poll GET /v1/jobs/{id} until it settles, then download GET /v1/jobs/{id}/content.

CALLING

Make your first call

# API Many quickstart — one key covers every model
curl https://apimany.com/v1/jobs \
  -H "Authorization: Bearer $APIMANY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_ID" \
  -d '{"model":"minimax/speech-2.6-turbo","bitrate":"32000","channel":"1","emotion":"happy","english_normalization":false,"format":"mp3","pitch":0,"sample_rate":"8000","speed":1,"volume":1,"prompt":"Warm analog synth pad with a slow rising filter."}'

Accepted parameters

FieldKindAcceptedNeeded
bitrateinteger32000 · 64000 · 128000 · 256000optional
channelstring1 · 2optional
emotionstringhappy · sad · angry · fearful · disgusted · surprised · neutraloptional
english_normalizationbooleandefault falseoptional
formatstringmp3 · wav · pcm · flacoptional
language_booststring—optional
pitchnumberdefault 0optional
sample_rateinteger8000 · 16000 · 22050 · 24000 · 32000 · 44100optional
speednumberdefault 1optional
textstring—required
voice_idstring—required
volumenumberdefault 1optional

ONLINE TEST

Send a real job from this page

The request runs against this site's own /v1/jobs using your signed-in balance, or an API key if you are not signed in. A pasted key stays in this browser tab and is never stored; the result is charged at the quoted USD price.

Or sign in to run with your account balance.

GOOD TO KNOW

Integration questions

Can I reach Speech 2.6 Turbo with my existing API Many key?
Speech 2.6 Turbo is one route in the shared gateway, so the same key, balance and limits apply. Enable it per route, then confirm the live id and rate with an authenticated GET /v1/models call.
What request shape does Speech 2.6 Turbo expect?
Send JSON to POST /v1/jobs with the model id and your parameters, plus a unique Idempotency-Key header. The gateway validates the body, reserves the quoted USD amount and returns a job you poll.
How is Speech 2.6 Turbo billed?
Each job is quoted for your exact parameters before it runs, from $0.081. A confirmed rejection releases the reservation; a settled job is charged at its quote.
Which fields does Speech 2.6 Turbo accept?
Recognised fields are bitrate, channel, emotion, english_normalization, format, language_boost, pitch, sample_rate, speed, text. Anything else is refused with a 400 instead of being forwarded upstream.
Is Speech 2.6 Turbo live right now?
Availability is set per route. Read the authenticated model list to see whether minimax/speech-2.6-turbo is enabled, with its exact specification and rate.

KEEP EXPLORING

Nearby models