WaveSpeedAI MiniMax Speech 2.6 Turbo

Convert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.

Setup

Install the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:

npm install -g @wavespeed/cli
wavespeed login          # opens https://wavespeed.ai/accesskey and stores the key
wavespeed status         # confirms you are signed in

For CI or one-off shells, WAVESPEED_API_KEY in the environment also works.

Prefer MCP tools over shell commands? The same platform is exposed by @wavespeed/mcp (npx -y @wavespeed/mcp; tools search_models, get_model_schema, get_price, upload_file, run_model, get_prediction). It shares the CLI's stored login. Every example below maps one-to-one onto run_model with the same model id and input fields.

Quick Start

OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \
  -i text="Hello, welcome to WaveSpeed AI!" \
  -i voice_id="English_CalmWoman" \
  --json | jq -r '.outputs[0]')

API Endpoint

Model ID: minimax/speech-2.6-turbo

Convert text to speech with configurable voice, emotion, speed, pitch, and audio format.

Parameters

Example

OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \
  -i text="The quick brown fox jumps over the lazy dog." \
  -i voice_id="English_expressive_narrator" \
  -i speed=1.0 \
  -i pitch=0 \
  -i emotion="neutral" \
  -i format="mp3" \
  -i sample_rate=24000 \
  -i bitrate=128000 \
  --json | jq -r '.outputs[0]')

Pause Control

Insert pauses in speech using <#x#> syntax where x is seconds (0.01-99.99):

OUTPUT_URL=$(wavespeed run minimax/speech-2.6-turbo \
  -i text="And the winner is <#2.0#> WaveSpeed AI!" \
  -i voice_id="English_CaptivatingStoryteller" \
  --json | jq -r '.outputs[0]')

Voice IDs

English Voices (Popular)

General Voices

Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl

Special Voices

whisper_man, whisper_woman_1, angry_pirate_1, massive_kind_troll, movie_trailer_deep, peace_and_ease

Other Languages

Voices are available for: Chinese (Mandarin), Cantonese, 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.

Voice IDs follow the pattern {Language}_{VoiceName} (e.g., Japanese_KindLady, Korean_SweetGirl, French_CasualMan).

Supported Languages

For language_boost: Chinese, Chinese,Yue, 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

Pricing

$0.06 per 1,000 characters.

CLI tips

# Inspect the live input schema before running (fields, enums, defaults)
wavespeed run minimax/speech-2.6-turbo -h

# Quote the price first
wavespeed price minimax/speech-2.6-turbo -p "..." -i key=value

# Save outputs to disk instead of only printing URLs
wavespeed run minimax/speech-2.6-turbo -p "..." --json --download "./out/{index}.{ext}"

# Local files: prefix the path with @ and the CLI uploads it and passes the hosted URL
wavespeed run minimax/speech-2.6-turbo -i <field>=@./local-file.png --json

# Recover a result if the run was interrupted (the id is in the --json output)
wavespeed show <id>

run --json prints { id, model, prompt, outputs: [url, ...], saved: [path, ...], elapsed_ms, raw }. Read outputs[0] for the result URL.

Security constraints

• Never ask for the key in chat: wavespeed login handles auth; if wavespeed status says signed out, ask the user to run it.
• Local files only via @: bare paths are passed through untouched and the model will reject them. Only @-prefixed values upload.
• No arbitrary URL loading: only pass media URLs the user provided or that came back from a previous run.
• Input validation: only pass parameters documented above; confirm with wavespeed run <model> -h when unsure.