Build next-gen apps with speech-2.6-hd

Pricing

TokenLab Price

$70.00

Per Character

Discount: 30%

	Official Price	TokenLab Price	Discount
Input	$100.00	$70.00	30%
Output	Free	Free	-

One-click test

Test speech-2.6-hd in Web Agent. Run a minimal audio request at /v1/audio/speech, then show request body, response, and integration notes.

API workbench

The default route for production. The code sample below uses this endpoint with the format you pick.

ttsTokenLab endpoint

POST/v1/audio/speech

curl -X POST "https://api.tokenlab.sh/v1/audio/speech" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "tts",
  "voice_id": "male-qn-qingse",
  "response_format": "mp3",
  "speed": 1,
  "model": "speech-2.6-hd",
  "input": "Hello from TokenLab.",
  "voice": "alloy"
}'

Use cases

Voice UX

Generate narration, onboarding audio, and spoken UI responses.

Side-by-side test

See real response quality, latency, and price before this becomes your production default.

Prompt examples

Generate calm onboarding narration for a developer tool.

Send the smallest possible request and walk me through every response field.

Compare this model with a cheaper one in the same category — when is each worth it?

FAQ

How much does speech-2.6-hd cost?

On TokenLab, speech-2.6-hd costs $70.0000 per 1M input tokens and $0.0000 per 1M output tokens. Cache and per-request prices show in the pricing table when they apply.

What is speech-2.6-hd best for?

speech-2.6-hd is a strong fit for Text to Speech. You can call it through TokenLab with one API key.

How do I call the speech-2.6-hd API?

Get a TokenLab API key, then send your request to https://api.tokenlab.sh/v1/audio/speech. The API workbench above has a recommended endpoint and copy-ready code.

Which endpoint should speech-2.6-hd use?

Use https://api.tokenlab.sh/v1/audio/speech as the default for speech-2.6-hd. If a provider-native format is supported, the API workbench shows that endpoint too.

Can I test speech-2.6-hd before integrating it?

Yes. Try in Web Agent opens a ready test for speech-2.6-hd and keeps your prompt after sign-in, so you don’t lose context.

Which operations does speech-2.6-hd support?

speech-2.6-hd supports tts. Pick an operation in the API workbench above to see the matching endpoint and code sample.

Related Models