Terminal
Terminal/Skill
Text to speech and speech to text on Together AI, covering streaming voice, transcription, translation, and speaker diarization for audio apps.
By Together AI
Works with
npx skills add togethercomputer/skills --skill together-audioUse Together AI audio APIs for:
together-chat-completions for text-only generationtogether-video or together-images for visual generation workflowstogether-dedicated-model-inference only when the audio model itself must be hosted on dedicated infrastructuretogether>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".client.audio.speech.create() for TTS.BinaryAPIResponse; call response.write_to_file(path) to save it. Do NOT use stream_to_file (it does not exist on this object).stream=True) returns a Stream of AudioSpeechStreamChunk objects. Iterate chunks, check chunk.type, and decode base64.b64decode(chunk.delta) for audio data. There is no file-writing helper on the stream object.client.audio.transcriptions.create() for transcription and client.audio.translations.create() for translation.file=; for longer audio, split into ≤ 4 h chunks. See the Limits section of references/stt-models.md.