Skip to main content
Bland Speech is text-to-speech built for live conversation. It handles partial LLM output, pauses, names, numbers, emotion, and mid-sentence changes while returning audio with low latency. New here? One curl command gets you an audio file, and the quickstart ends by pointing you at the right endpoint for what you are building.

​
Start with realtime TTS

WSS /v2/tts/ws is the primary TTS endpoint for new conversational applications. Send LLM tokens as they arrive. Bland buffers them into useful speech segments, keeps the voice session warm across turns, and supports interruption by replacing or cancelling the active turn.

Realtime quickstart

Stream text token by token and receive binary audio before the turn finishes.

Realtime concepts

Understand buffering, turns, preemption, cancellation, playback, and billing.

WebSocket reference

Review every client message, server event, audio format, limit, and error.

Migration guides

Move from ElevenLabs, Cartesia, Deepgram, PlayHT, Resemble, Google, or Polly.

​
Other ways to generate speech

Synthesize Speech (HTTP)

Send one complete input string and receive raw streaming audio or a WAV file.

OpenAI-compatible speech

Keep an OpenAI SDK and change its base URL, key, and model.

Speech Studio

Write, direct, and synthesize speech from the dashboard.

Clone a voice

Create a Bland voice from a short reference recording.

​
Get the delivery right

Choosing a voice

Built-in voices, cloning, and the defaults each voice carries.

Writing for speech

Pauses, numbers, punctuation, and the expressiveness and stability controls.
For the fastest path, choose a BTTS_V3 voice and request 48 kHz PCM. The model renders at that rate natively, so no sample-rate conversion is required.

​
Browser clients

Do not expose a Bland API key in browser code. Your backend should mint a five-minute stream token, then the browser can connect to:

​
Limits and pricing

Speech is billed per character, with delivery-aware settlement. A realtime connection holds one concurrency slot until it closes. Review Speech Limits and the WebSocket billing rules before sizing a production integration.
Docs for agents: llms.txt