Patch parameters
Translated
| OpenAI | ElevenLabs | Teen V1 behavior |
|---|---|---|
input | text | Speech text |
model | model_id | Selects routing, then becomes teen-v1 |
voice | voice_id | Uses a TeenageWorks ID or provider voice fallback |
response_format | output_format | Maps to PCM, MP3, or WAV |
cfg_value | cfg_value | Passes through unchanged |
reference_audio | reference_audio | Inline reference recording |
reference_audio_format | reference_audio_format | Reference recording format |
timeout | request_options.timeout_in_seconds | Sets the TeenageWorks request timeout |
The patch adds the required language value internally.
Ignored with a warning
OpenAI instructions and speed are ignored.
ElevenLabs seed, enable_logging, optimize_streaming_latency, language_code, voice_settings, pronunciation_dictionary_locators, previous_text, next_text, previous_request_ids, next_request_ids, use_pvc_as_ivc, apply_text_normalization, and apply_language_text_normalization are ignored. The server controls the generation seed.
Each ignored value emits TeenageWorksUnsupportedParameterWarning. Provider voice fallback emits TeenageWorksVoiceMappingWarning.
Rejected
- Unsupported codecs raise
UnsupportedAudioFormatError. - Timestamp methods,
temperature,voice_description,reference_transcript, andreference_textraiseUnsupportedFeatureError. - Unknown arguments raise
TypeError.
Nothing is silently discarded.
When inline reference audio is present, the provider voice ID is not used.