Skip to main content

Text to Speech

Category: AI & ML
Node id: text-to-speech
Maturity: beta
Risk tier: B

Standards: HIPAA, GDPR

Synthesizes speech from text using ElevenLabs or Google Cloud Text-to-Speech, with per-call voice and language selection and telephony-ready output formats (8 kHz μ-law) alongside mp3 and PCM.

What it does​

  • Speech synthesis via ElevenLabs (flash and multilingual models)
  • Speech synthesis via Google Cloud Text-to-Speech
  • Telephony-ready 8 kHz μ-law output for carrier media
  • Per-item voice and language override from upstream node outputs
  • EU-resident synthesis by pointing api_url at a Google regional endpoint
  • Voice tuning: stability, similarity boost and speaking rate

Use cases​

  • Speak an appointment reminder to a patient during an automated call
  • Render the agent side of a voice-call workflow into carrier audio
  • Produce audio versions of patient instructions for accessibility
  • Generate IVR prompts in Spanish, Catalan and English from one pipeline

Runtime​

  • Performance tier: medium
  • Execution mode: batch
  • Default timeout: 60 seconds
  • Retryable: Yes (default 2 retries)

Input ports​

NameTypeRequiredDescription
texttextYesThe text to speak
voice_idtextNoOptional per-item voice override, taking precedence over the configured voice_id
languagetextNoOptional per-item language override (BCP-47 or ISO 639-1)

Output ports​

NameTypeRequiredDescription
audio_datatextNoBase64-encoded synthesized audio
mime_typetextNoMIME type of the returned audio
formattextNoShort format name of the returned audio
bytesnumberNoSize of the decoded audio in bytes
voice_idtextNoVoice actually used, after defaults and overrides
providertextNoProvider that produced the audio
successbooleanNoWhether synthesis succeeded

Settings​

Basic​

SettingNameTypeRequiredDefaultAllowed valuesDescription
ProviderproviderenumNoelevenlabselevenlabs, googleSpeech synthesis provider
Voicevoice_idstringNoProvider voice identifier. Empty uses the provider default.
LanguagelanguagestringNoBCP-47 or ISO 639-1 language code (for example es-ES, ca, en)
Output FormatformatenumNomp3mp3, wav, pcm, ulaw, oggAudio encoding to produce. Use ulaw for telephony.

Auth​

SettingNameTypeRequiredDefaultAllowed valuesDescription
API Keyapi_keysecretYesElevenLabs API key, or Google Cloud API key for the google provider

Advanced​

SettingNameTypeRequiredDefaultAllowed valuesDescription
ModelmodelstringNoProvider model id. Empty uses the low-latency default (eleven_flash_v2_5 for ElevenLabs).
Sample Rate (Hz)sample_ratenumberNo0min 0; max 48000Output sample rate. 0 uses the provider default (8000 for ulaw).
Speaking RatespeednumberNo1min 0.25; max 4Speed multiplier around 1.0
StabilitystabilitynumberNo0.5min 0; max 1ElevenLabs voice stability; lower is more expressive, higher is more consistent
Similarity BoostsimilaritynumberNo0.75min 0; max 1ElevenLabs similarity to the original voice
API Endpointapi_urlstringNoOverride the provider endpoint. Use a Google EU regional endpoint to keep synthesis inside the EU.
Timeout (seconds)timeoutnumberNo60min 5; max 300Request timeout

Errors​

CodeDescription
API_KEY_REQUIREDNo API key configured for the selected provider
TEXT_REQUIREDThe text input was missing or empty
INVALID_PROVIDERprovider is not one of: elevenlabs, google
INVALID_FORMATformat is not one of: mp3, wav, pcm, ulaw, ogg
SYNTHESIS_FAILEDThe provider rejected the request or returned no audio

Runtime notes​

  • audio_data is base64-encoded — decode it before writing to a file or handing it to a carrier
  • format=ulaw returns 8 kHz μ-law, the encoding telephony carriers expect; every other format is for playback or storage
  • voice_id and language inputs override the configured values, so one node can serve a multi-language run
  • ElevenLabs voice ids are opaque strings; Google voice names carry their language as a prefix (es-ES-Neural2-A) and set the language automatically
  • stability, similarity and model apply to ElevenLabs only; Google ignores them
  • Provider choice is a data-residency decision: ElevenLabs processes in the US, Google Cloud TTS can be pinned to an EU endpoint via api_url

See Build any workflow for how to put nodes together and Ports, types and data flow for how port types connect.

Something unclear? Send documentation feedback by email.