Migrate from Amazon Polly

Choose the migration based on when your text becomes available.

For a complete string and a downloadable response, use Synthesize Speech (HTTP).
For partial LLM text and conversational interruptions, use the Realtime TTS Quickstart.

Complete text

Map a Polly SynthesizeSpeech request to Bland as follows:

Amazon Polly	Bland `POST /v2/tts`
AWS credentials and region	Bland API key
`Text`	`text`
`VoiceId`	Bland voice UUID in `voice`
`OutputFormat: "pcm"`	`audio.encoding: "pcm_s16le"`, `audio.container: "raw"`
`OutputFormat: "mp3"`	No native equivalent; request WAV or raw audio
`SampleRate` string	`audio.sample_rate` number

curl -X POST "https://api.bland.ai/v2/tts" \
  -H "Authorization: Bearer $BLAND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from Bland.",
    "voice": "29158307-9893-4149-8a75-bc9ce313d64e",
    "audio": {
      "encoding": "pcm_s16le",
      "sample_rate": 24000,
      "container": "wav"
    }
  }' \
  --output speech.wav

Polly SSML, engine selection, lexicons, and speech marks do not map directly. Bland supports pause markers and normalized expressiveness and stability controls on its HTTP endpoint.

Realtime LLM input

Polly’s standard synthesis request takes one complete Text value. Bland’s WebSocket can start speaking while the LLM is still producing tokens:

for await (const token of llmTextStream) {
  ws.send(
    JSON.stringify({
      type: "speak",
      context_id: turnId,
      text: token,
    }),
  );
}

ws.send(JSON.stringify({ type: "end_of_turn", context_id: turnId }));

See the Amazon Polly synthesis example, Bland HTTP reference, and Bland WebSocket reference.

Docs for agents: llms.txt

⌘I

Get Started

Realtime Speech

HTTP Speech

Migrate

Voice Cloning

Voices

Discovery

Samples

Generation History

Models

Tooling

Migrate from Amazon Polly

Complete text

Realtime LLM input

​Complete text

​Realtime LLM input

Complete text

Realtime LLM input