Release Notes
Build
Analyze
watsonx Orchestrate Developer Edition
watsonx Orchestrate MCP Server
Legal notices
Create Voice Configuration
Copy
Ask AI
curl --request POST \
--url https://{api_endpoint}/api/v1/voice_configurations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"speech_to_text": {
"provider": "<string>",
"watson_stt_config": {
"api_url": "<string>",
"model": "<string>",
"api_key": "<string>",
"bearer_token": "<string>",
"end_of_phrase_silence_time": 123,
"background_audio_suppression": 0.5,
"language_customization_id": "<string>",
"inactivity_timeout": 0,
"profanity_filter": true,
"smart_formatting": true,
"speaker_labels": true,
"redaction": true,
"low_latency": true,
"learning_opt_out": true,
"watson_metadata": "<string>",
"smart_formatting_version": 1,
"customization_weight": 0.5,
"character_insertion_bias": 0
},
"emotech_stt_config": {
"api_url": "<string>",
"api_key": "<string>",
"positive_speech_threshold": 0.25,
"negative_speech_threshold": 0.25,
"partial_interval": 500,
"silence_threshold": 500
}
},
"text_to_speech": {
"provider": "<string>",
"watson_tts_config": {
"api_url": "<string>",
"voice": "<string>",
"api_key": "<string>",
"bearer_token": "<string>",
"rate_percentage": 0,
"pitch_percentage": 0,
"language": "<string>",
"customization_id": "<string>",
"meta_id": "<string>",
"learning_opt_out": true
},
"emotech_tts_config": {
"api_url": "<string>",
"api_key": "<string>",
"voice": "<string>"
},
"elevenlabs_tts_config": {
"model_id": "<string>",
"voice_id": "<string>",
"api_key": "<string>",
"apply_text_normalization": "<string>",
"language_code": "<string>",
"optimize_streaming_latency": 123,
"apply_language_text_normalization": true,
"pronunciation_dictionary_locators": [
{
"pronunciation_dictionary_id": "<string>",
"version_id": "<string>"
}
],
"seed": 123,
"previous_text": "<string>",
"next_text": "<string>",
"voice_settings": {
"speed": 1,
"style": 0,
"stability": 0.5,
"similarity_boost": 0.75,
"use_speaker_boost": true
}
}
},
"llm_aggregation_timeout_seconds": 0.8,
"language": "en-us",
"additional_languages": {},
"dtmf_input": {
"inter_digit_timeout_ms": 2500,
"termination_key": "<string>",
"maximum_count": 123,
"ignore_speech": true
},
"vad": {
"enabled": true,
"provider": "silero_vad",
"silero_vad_config": {
"confidence": 0.7,
"start_seconds": 0.2,
"stop_seconds": 0.8,
"min_volume": 0.6
}
}
}
'Copy
Ask AI
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Voice Configurations
Create Voice Configuration
POST
/
v1
/
voice_configurations
Create Voice Configuration
Copy
Ask AI
curl --request POST \
--url https://{api_endpoint}/api/v1/voice_configurations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"speech_to_text": {
"provider": "<string>",
"watson_stt_config": {
"api_url": "<string>",
"model": "<string>",
"api_key": "<string>",
"bearer_token": "<string>",
"end_of_phrase_silence_time": 123,
"background_audio_suppression": 0.5,
"language_customization_id": "<string>",
"inactivity_timeout": 0,
"profanity_filter": true,
"smart_formatting": true,
"speaker_labels": true,
"redaction": true,
"low_latency": true,
"learning_opt_out": true,
"watson_metadata": "<string>",
"smart_formatting_version": 1,
"customization_weight": 0.5,
"character_insertion_bias": 0
},
"emotech_stt_config": {
"api_url": "<string>",
"api_key": "<string>",
"positive_speech_threshold": 0.25,
"negative_speech_threshold": 0.25,
"partial_interval": 500,
"silence_threshold": 500
}
},
"text_to_speech": {
"provider": "<string>",
"watson_tts_config": {
"api_url": "<string>",
"voice": "<string>",
"api_key": "<string>",
"bearer_token": "<string>",
"rate_percentage": 0,
"pitch_percentage": 0,
"language": "<string>",
"customization_id": "<string>",
"meta_id": "<string>",
"learning_opt_out": true
},
"emotech_tts_config": {
"api_url": "<string>",
"api_key": "<string>",
"voice": "<string>"
},
"elevenlabs_tts_config": {
"model_id": "<string>",
"voice_id": "<string>",
"api_key": "<string>",
"apply_text_normalization": "<string>",
"language_code": "<string>",
"optimize_streaming_latency": 123,
"apply_language_text_normalization": true,
"pronunciation_dictionary_locators": [
{
"pronunciation_dictionary_id": "<string>",
"version_id": "<string>"
}
],
"seed": 123,
"previous_text": "<string>",
"next_text": "<string>",
"voice_settings": {
"speed": 1,
"style": 0,
"stability": 0.5,
"similarity_boost": 0.75,
"use_speaker_boost": true
}
}
},
"llm_aggregation_timeout_seconds": 0.8,
"language": "en-us",
"additional_languages": {},
"dtmf_input": {
"inter_digit_timeout_ms": 2500,
"termination_key": "<string>",
"maximum_count": 123,
"ignore_speech": true
},
"vad": {
"enabled": true,
"provider": "silero_vad",
"silero_vad_config": {
"confidence": 0.7,
"start_seconds": 0.2,
"stop_seconds": 0.8,
"min_volume": 0.6
}
}
}
'Copy
Ask AI
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Required string length:
1 - 128Show child attributes
Show child attributes
Required string length:
1 - 128Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 256Required string length:
1 - 2048Required string length:
1 - 2048Background audio suppression level (0.0 to 1.0). Default 0.0
Required range:
0 <= x <= 1Language customization ID
Required string length:
1 - 256Seconds of inactivity before the service stops listening. Default 30
Required range:
x >= -1Filter profanity in the transcript. Default true
Enable smart formatting (beta). Default false
Enable speaker labels (beta). Default false
Enable PII redaction (beta). Default false
Enable low latency mode. Default false
Opt out of data collection for learning. Default true
Value for x-watson-metadata header.
Required string length:
1 - 512Version of smart formatting to use.
Required range:
x >= 0Weight for custom language model (0.0 to 1.0). Default 0.5
Required range:
0 <= x <= 1Bias for character insertion (-1.0 to 1.0). Default 0.0
Required range:
-1 <= x <= 1Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 2048Confidence threshold above which audio is classified as speech, default is 0.25
Confidence threshold below which audio is classified as non-speech, default is 0.25
Time interval (in ms) between partial transcription results, default is 500 ms.
Silence duration (in ms) after speech used to determine end of utterance, default is 1500 ms.
Show child attributes
Show child attributes
Required string length:
1 - 128Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 128Required string length:
1 - 2048Required string length:
1 - 2048Rate percentage for speech synthesis, default is 0
Pitch percentage for speech synthesis, default is 0
Language code for the voice, e.g., 'en-US'
Required string length:
2 - 16Custom ID for the Watson TTS service
Required string length:
1 - 256Meta ID for the Watson TTS service
Required string length:
1 - 256Set to true to opt out of data collection for learning purposes
Show child attributes
Show child attributes
The ID of the ElevenLabs model to use
Required string length:
1 - 128The ID of the ElevenLabs voice to use
Required string length:
1 - 128ElevenLabs API key
Required string length:
1 - 2048Whether to apply text normalization
Language code for the voice, e.g., 'en', 'es'
Required string length:
2 - 16Optimize streaming latency (0-4)
Whether to apply language-specific text normalization
text_to_speech.elevenlabs_tts_config.pronunciation_dictionary_locators
ElevenLabsPronounciationDict · object[] | null
List of pronunciation dictionary locators
Show child attributes
Show child attributes
Seed for deterministic audio generation
Previous text for context
Next text for context
Voice settings for the ElevenLabs TTS
Show child attributes
Show child attributes
Speech speed. Defaults to 1.0
Style exaggeration: the higher the value, the more computational resources are used. Defaults to 0.0
Stability: how stable the voice is and the randomness between each generation. Defaults to 0.5
Similarity boost: how closely the AI should adhere to the original voice. Defaults to 0.75
Whether to use speaker boost. Defaults to true
Maximum time to wait for additional transcription content before pushing aggregated result.
Default language code, e.g., 'en-us'
Required string length:
2 - 16Additional language configurations keyed by language code
Show child attributes
Show child attributes
Voice configuration for a specific language
Show child attributes
Show child attributes
Show child attributes
Show child attributes
Required string length:
1 - 128Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 128Required string length:
1 - 2048Required string length:
1 - 2048Rate percentage for speech synthesis, default is 0
additional_languages.{key}.text_to_speech.watson_tts_config.pitch_percentage
integer | null
default:0
Pitch percentage for speech synthesis, default is 0
Language code for the voice, e.g., 'en-US'
Required string length:
2 - 16Custom ID for the Watson TTS service
Required string length:
1 - 256Meta ID for the Watson TTS service
Required string length:
1 - 256Set to true to opt out of data collection for learning purposes
Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 2048Required string length:
1 - 128Show child attributes
Show child attributes
The ID of the ElevenLabs model to use
Required string length:
1 - 128The ID of the ElevenLabs voice to use
Required string length:
1 - 128ElevenLabs API key
Required string length:
1 - 2048additional_languages.{key}.text_to_speech.elevenlabs_tts_config.apply_text_normalization
string | null
Whether to apply text normalization
Language code for the voice, e.g., 'en', 'es'
Required string length:
2 - 16additional_languages.{key}.text_to_speech.elevenlabs_tts_config.optimize_streaming_latency
integer | null
Optimize streaming latency (0-4)
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.apply_language_text_normalization
boolean | null
Whether to apply language-specific text normalization
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.pronunciation_dictionary_locators
ElevenLabsPronounciationDict · object[] | null
List of pronunciation dictionary locators
Show child attributes
Show child attributes
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.pronunciation_dictionary_locators.pronunciation_dictionary_id
string
required
ID of the pronunciation dictionary
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.pronunciation_dictionary_locators.version_id
string
required
Version ID of the pronunciation dictionary
Seed for deterministic audio generation
Previous text for context
Next text for context
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings
ElevenLabsVoiceSettings · object
Voice settings for the ElevenLabs TTS
Show child attributes
Show child attributes
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings.speed
number
default:1
Speech speed. Defaults to 1.0
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings.style
number
default:0
Style exaggeration: the higher the value, the more computational resources are used. Defaults to 0.0
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings.stability
number
default:0.5
Stability: how stable the voice is and the randomness between each generation. Defaults to 0.5
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings.similarity_boost
number
default:0.75
Similarity boost: how closely the AI should adhere to the original voice. Defaults to 0.75
additional_languages.{key}.text_to_speech.elevenlabs_tts_config.voice_settings.use_speaker_boost
boolean
default:true
Whether to use speaker boost. Defaults to true
Show child attributes
Show child attributes
Required string length:
1 - 128Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 256Required string length:
1 - 2048Required string length:
1 - 2048additional_languages.{key}.speech_to_text.watson_stt_config.end_of_phrase_silence_time
number | null
additional_languages.{key}.speech_to_text.watson_stt_config.background_audio_suppression
number | null
Background audio suppression level (0.0 to 1.0). Default 0.0
Required range:
0 <= x <= 1Language customization ID
Required string length:
1 - 256Seconds of inactivity before the service stops listening. Default 30
Required range:
x >= -1Filter profanity in the transcript. Default true
Enable smart formatting (beta). Default false
Enable speaker labels (beta). Default false
Enable PII redaction (beta). Default false
Enable low latency mode. Default false
Opt out of data collection for learning. Default true
Value for x-watson-metadata header.
Required string length:
1 - 512Version of smart formatting to use.
Required range:
x >= 0Weight for custom language model (0.0 to 1.0). Default 0.5
Required range:
0 <= x <= 1Bias for character insertion (-1.0 to 1.0). Default 0.0
Required range:
-1 <= x <= 1Show child attributes
Show child attributes
Required string length:
1 - 2048Required string length:
1 - 2048additional_languages.{key}.speech_to_text.emotech_stt_config.positive_speech_threshold
number | null
default:0.25
Confidence threshold above which audio is classified as speech, default is 0.25
additional_languages.{key}.speech_to_text.emotech_stt_config.negative_speech_threshold
number | null
default:0.25
Confidence threshold below which audio is classified as non-speech, default is 0.25
additional_languages.{key}.speech_to_text.emotech_stt_config.partial_interval
integer | null
default:500
Time interval (in ms) between partial transcription results, default is 500 ms.
additional_languages.{key}.speech_to_text.emotech_stt_config.silence_threshold
integer | null
default:500
Silence duration (in ms) after speech used to determine end of utterance, default is 1500 ms.
Show child attributes
Show child attributes
The amount of time (ms) to wait for a new DTMF digit, default is 2500 ms.
The DTMF termination key that signals the end of DTMF input.
Maximum number of digits a user can enter.
Disable speech recognition during collection of DTMF digits, default is true.
Show child attributes
Show child attributes
Enable Voice Activity Detection, default is true.
Required string length:
1 - 128Show child attributes
Show child attributes
The confidence threshold for speech detection (between 0.0 and 1.0), default is 0.7
The time in seconds speech must be detected before transitioning to SPEAKING state, default is 0.2
The time in seconds silence must be detected before transitioning to QUIET state, default is 0.8
The minimum audio volume threshold for speech detection (between 0.0 and 1.0), default is 0.6
Response
Successful Response
⌘I