speech-2.6-turbo
Speech 2.6 Turbo synthesizes multilingual speech and targets low response latency.
About the model
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Lines for a voice workflow
Speech 2.6 Turbo is a speed-focused speech synthesis variant. The manufacturer describes it for voice assistants and interactive scenarios in which text becomes a response incrementally. The model retains the natural intonation of the Speech 2.6 generation and can process specialized written forms.
Text that needs to be pronounced correctly
The model is designed to read dates, phone numbers, monetary amounts, URLs and email addresses without each item first being manually rewritten. This processing is useful in dynamic messages where numbers and notation occur alongside ordinary words. The manufacturer describes handling these formats in several languages.
Fluency and emotion control
Speech 2.6 supports Fluent LoRA: retaining recognizable timbre with more fluent delivery. This capability concerns use of an already prepared voice; separate preparation of a clone is not part of an ordinary text request. The family includes 40 languages, including Russian.
Turbo provides seven main emotions and the additional fluent and whisper modes. The model can choose emotional coloration itself from the content or use a specified state. Vocal depth and pace can be changed independently of the text.
Voice, pauses and pronunciation
MiniMax provides voice selection and control over pace, volume and pitch. Speed ranges from 0.5–2, volume is above 0 and up to 10, and pitch adjustment ranges from −12 to 12. Emotion can be left to the model according to the text's meaning or specified manually: joy, sadness, anger, fear, disgust, surprise or calm.
Pronunciation can be refined using a replacement dictionary and phonetic notation; these provide the International Phonetic Alphabet, Chinese pinyin and Japanese reading variants. Pauses are inserted between spoken passages in the range 0.01–99.99 seconds. Pause duration is specified to two decimal places; markers are placed between spoken passages and not consecutively. These settings help align names, abbreviations and ambiguous words with the intended narration.
Receiving audio
Synthesis accepts text of fewer than 10,000 characters. For long text exceeding 3000 characters, the manufacturer recommends streaming output; receiving completed audio in full is also provided. General synthesis settings include MP3, PCM, FLAC, WAV, Opus and G.711 μ-law variants, in mono or stereo; the available formats for a specific request are determined by Ailoot's controls.
In this Ailoot card, text is converted into speech audio. Turbo's purpose concerns synthesis speed, but no fixed response time is promised here; the listed settings reflect manufacturer capabilities and apply within the available access method.
Additional audio settings include sample rates of 8, 16, 22.05, 24, 32 and 44.1 kHz. MP3 provides bitrates of 32, 64, 128 or 256 kbps. Voice coloration can also be changed and one effect applied: spacious echo, hall echo, telephone sound or a robotic voice. Voice-modification effects are supported for MP3, WAV and FLAC when receiving the audio in full, and only for MP3 when streaming. G.711 μ-law formats use an 8 kHz sample rate. These capabilities belong to MiniMax's synthesis settings.
The manufacturer provides speech-text synchronization: sentence timestamps, word timestamps or word timestamps during incremental output. This result helps align speech with displayed text. This additional capability requires support for the corresponding response format.
Ailoot · Text to speech POST /v1/audio/speech speech-2.6-turbo
speech-2.6-turboOverview
Speech 2.6 Turbo synthesizes multilingual speech and targets low response latency.
- Accepted inputs
- Text
- Results
- speech
Available in Ailoot · inputs & methods
Ailoot · Text to speech POST /v1/audio/speech
- Input types
text- Output types
speech- Output format
- mp3
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits speech-2.6-turbo | Default— |
Fieldinput | Typestring | RequirementRequired | Values & limits Minimum length: 1 Maximum length (exclusive): 10,000 Unit: Unicode characters | Default— |
Fieldvoice | Typestring | RequirementRequired | Values & limits Pattern: ^[A-Za-z0-9_-]{1,128}$ | Default— |
Fieldresponse_format | Typestring | RequirementOptional | Values & limits mp3 | Default— |
Input material combinations
text_to_speech · Required: input
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractnull |
Parameteroptional_controls | Contractnull |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Method shapes and IDs are exact; supplier capability is separate from admission.
Pricing
Ailoot method rates
POST /v1/audio/speech- Input
- $60.00 per 1 million characters
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot · Text to speech
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 narration script}"
export AILOOT_TEXT_FILE
: "${AILOOT_VOICE_ID:?Set the actual accepted voice ID for this model}"
export AILOOT_VOICE_ID
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "speech-2.6-turbo", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]=text
import re
voice=os.environ["AILOOT_VOICE_ID"]
if not re.fullmatch(r"[A-Za-z0-9_-]{1,128}",voice):raise SystemExit("Set an actual accepted voice ID")
p["voice"]=voice
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/speech \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o speech.mp3
Receive and save results
Ailoot · Text to speech
mp3
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}
Keep all completed results
Keep every complete returned response, file and content part.
Keep the complete binary result and headers. If JSON/multiple outputs are returned, retain every data item and fetch each actual signed asset URL.
If the original response needs checking
Retain original operation_id/X-Client-Request-ID for reconciliation without resubmission; no dedicated audio poll route.
Response fields
| Field | Type |
|---|---|
Fieldbinary audio | Typebytes |
Fieldresponse headers | Typeheaders |
Errors and next steps
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Aliases
Model aliases
Ailoot speech-2.6-turbo
Method path aliases
Use the method paths shown above.
Related caller IDs
FAQ · speech-2.6-turbo
- What inputs and results are available?
POST /v1/audio/speech·speech-2.6-turbo:text→speech- Which fields does the request use?
POST /v1/audio/speech·speech-2.6-turbo:model,input,voice,response_format