VoiceThere
Sign up

AWS speech on VoiceThere

Amazon Transcribe streaming STT and Polly neural TTS on VoiceThere cloud with IAM access keys in project secrets.

Overview of all vendors: STT & TTS vendors.

What it is

Amazon Transcribe streaming handles STT; Amazon Polly neural voices handle TTS. VoiceThere signs requests with IAM access keys you store as project secrets.

Home: Transcribe streaming, Amazon Polly

Set up on VoiceThere

  • Dashboard: Project Settings → Voice (STT / TTS). Pick aws on the leg this vendor supports. Add project secrets from the list below, then Deploy to cloud.
  • Secrets: Store keys as AGENT_* project secrets (see Agent environment & secrets).
  • API: Patch stt_provider / tts_provider on the project before deploy. See Control plane API.

Project secrets for this vendor

  • AGENT_AWS_ACCESS_KEY_ID: AWS access key id. IAM access key for Transcribe and Polly.
  • AGENT_AWS_SECRET_ACCESS_KEY: AWS secret access key. IAM secret for Transcribe and Polly.
  • AGENT_AWS_REGION: AWS region. Region for Transcribe streaming and Polly (e.g. eu-central-1).

CLI (after secrets exist):

voicethere projects voice set --project YOUR_PROJECT_ID \
  --stt-provider aws --tts-provider aws \
  --stt-language en-US --tts-voice Joanna

Models and voices you can pick

Project Voice settings in the dashboard lists every model and voice id VoiceThere accepts for this vendor. The same allowlists ship in the npm package @node-webrtc-rust/voice-catalog (pinned on your platform release).

STT examples: en-US, es-US

TTS voice examples: Joanna, Hala

What the implementation does

STT opens an AWS Transcribe streaming session for the configured language. Partials are available on the stream. TTS calls Polly neural synthesis with a full response body (not generative StartSpeechSynthesisStream).

Limitations

  • Requires AGENT_AWS_ACCESS_KEY_ID, AGENT_AWS_SECRET_ACCESS_KEY, and AGENT_AWS_REGION.
  • Polly generative streaming synthesis is not implemented.
  • Billed by AWS.

Official docs

← All documentation