capability hub

Speech

Speech recognition, synthesis, and speech-to-speech capability.

Identity source
Published changes629StatusactiveAliases0Relations0

Timeline

629 published changes

Open filtered feed
API change Importance 78/100 Confidence 100/100

Smart Turn for Streaming STT

Smart Turn for Streaming STT The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs . May 29

Release Importance 88/100 Confidence 100/100

Grok Voice 1.0 is available

Grok Voice 1.0 is available Grok Voice 1.0 is now available with the Speech to Speech API. To get started, check out the Speech to Speech docs . For more details, see our blog post . Apr 15

Action requiredReview affected integrations and migrate before the documented retirement boundary.
API change Importance 78/100 Confidence 100/100

Custom Voices

Custom Voices You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console. For more details, check out the Custom Voices docs and our blog post .

API change Importance 82/100 Confidence 100/100

Adjustable VAD threshold for Speech to Text

Adjustable VAD threshold for Speech to Text Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate that skips non-speech audio. Lower values transcribe quieter or noisier speech — useful for narrowband telephony — and 0 disables the gate. See the Speech to Text docs . July 17

API change Importance 78/100 Confidence 100/100

Smart Turn for Streaming STT

Smart Turn for Streaming STT The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs . May 29

Release Importance 88/100 Confidence 100/100

Grok Voice 2.0 deprecation

Grok Voice 2.0 deprecation grok-voice-2.0 is deprecated. To upgrade, set model to grok-voice-3.0 or grok-voice-latest , at the same price. See Upgrading from Grok Voice 2.0 . October 2

Action requiredReview affected integrations and migrate before the documented retirement boundary.
API change Importance 78/100 Confidence 100/100

Custom Voices

Custom Voices You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console. For more details, check out the Custom Voices docs and our blog post .

Product update Importance 78/100 Confidence 100/100

Adjustable VAD threshold for Speech to Text

Adjustable VAD threshold for Speech to Text Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate that skips non-speech audio. Lower values transcribe quieter or noisier speech — useful for narrowband telephony — and 0 disables the gate. See the Speech to Text docs . July 17

API change Importance 78/100 Confidence 100/100

Smart Turn for Streaming STT

Smart Turn for Streaming STT The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs . May 29

Release Importance 88/100 Confidence 100/100

Grok Voice 2.0 deprecation

Grok Voice 2.0 deprecation grok-voice-2.0 is deprecated. To upgrade, set model to grok-voice-3.0 or grok-voice-latest , at the same price. See Upgrading from Grok Voice 2.0 . October 2

Action requiredReview affected integrations and migrate before the documented retirement boundary.
API change Importance 78/100 Confidence 100/100

Custom Voices

Custom Voices You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console. For more details, check out the Custom Voices docs and our blog post .

API change Importance 78/100 Confidence 100/100

Smart Turn for Streaming STT

Smart Turn for Streaming STT The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs . May 29

Pricing Importance 88/100 Confidence 100/100

Grok Voice 2.0 deprecation

Grok Voice 2.0 deprecation grok-voice-2.0 is deprecated. To upgrade, set model to grok-voice-3.0 or grok-voice-latest , at the same price. See Upgrading from Grok Voice 2.0 . October 2

Action requiredReview affected integrations and migrate before the documented retirement boundary.
API change Importance 78/100 Confidence 100/100

Custom Voices

Custom Voices You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console. For more details, check out the Custom Voices docs and our blog post .

API change Importance 78/100 Confidence 100/100

Smart Turn for Streaming STT

Smart Turn for Streaming STT The streaming Speech to Text API now supports Smart Turn end-of-turn detection. When enabled via the smart_turn query parameter, an ML model predicts whether the speaker has finished their thought at silence boundaries — reducing false endpointing during dictation, number sequences, and mid-sentence pauses. Use smart_turn_timeout to set a maximum silence fallback. For more details, see the Smart Turn docs . May 29

Release Importance 88/100 Confidence 100/100

Grok Voice 1.0 is available

Grok Voice 1.0 is available Grok Voice 1.0 is now available with the Speech to Speech API. To get started, check out the Speech to Speech docs . For more details, see our blog post . Apr 15

Action requiredReview affected integrations and migrate before the documented retirement boundary.
API change Importance 78/100 Confidence 100/100

Custom Voices

Custom Voices You can now clone a voice from a short audio clip and use it across the Text-to-Speech and Speech to Speech APIs. Create and manage your voice catalog from the SpaceXSI console. For more details, check out the Custom Voices docs and our blog post .